GUARD: Sensitivity-aware Uncertainty Attribution for Safe Traditional and Learning-based Robot Control

arXiv:2509.23312 · cs.RO · Submitted 2025-09-27 · Read on arXiv

Listen

Radio episode about this paper

Transcript

Introduction to the show: ident: Robotics Radio. Generated commentary on the latest robotics and control papers.

Rosa: We're looking at the paper: "GUARD: Sensitivity-aware Uncertainty Attribution for Safe Traditional and Learning-based Robot Control".

Dev: Here's the gist of the paper. This paper presents GUARD (Guided robot control via Uncertainty attribution and probabilistic kernel optimization for Risk-aware Decision making) that combines traditional control with an uncertainty-aware perception technique using active learning with real-time capability for safe robot collision avoidance.

Rosa: By doing so, this manuscript addresses the central challenge in robotics of finding a reasonable compromise between traditional methods and learning algorithms to foster the development of safe, yet efficient and flexible applications.

Dev: The core idea is that safety is evaluated inversely by the uncertainty.

Rosa: Framework Components The GUARD framework unifies reactive model predictive contouring control (RMPCC) with an Iterative Closest Point (ICP) algorithm that enables the attribution of uncertainty sources online using active learning with real-time capability via a probabilistic kernel optimization technique.

Title and authors: Rosa: So we're looking at this paper called "GUARD: Sensitivity-aware Uncertainty Attribution for Safe Traditional and Learning-based Robot Control" by Johannes Gaus, Junheon Yoon, Woo-Jeong Baek, Seungwon Choi, Suhan Park, and Jaeheung Park. It sounds a bit dense with all those technical terms.

Dev: Yeah it is. The title itself points to combining traditional control with uncertainty attribution for safe robot systems. It suggests they are tackling that big problem of finding a balance between old methods and new learning algorithms in robotics, which is what the paper aims for >

Rosa: Exactly. Basically, they're suggesting that safety in these robot applications should be evaluated inversely by the uncertainty itself. Instead of assuming perfect perception or perfect control, you use the uncertainty to guide how safe things need to be >

Taro: That makes sense from a real-world standpoint. If the robot is really unsure about where an object is, it should probably act more cautiously, right? It's about handling when things go wrong in an unpredictable way >

Dev: Right. And this paper proposes a framework called GUARD to unify reactive model predictive contouring control with an uncertainty aware Iterative Closest Point algorithm that uses active learning for real-time capability >

The paper's summary: Rosa: So, the core idea of this GUARD framework is to use uncertainty attribution and probabilistic kernel optimization for risk-aware decision making to achieve safe robot collision avoidance >

Dev: It unifies reactive model predictive contouring control with an Iterative Closest Point algorithm that can attribute uncertainty sources online using active learning with real-time capability through a probabilistic kernel optimization technique >

Rosa: It's about taking those uncertainties from perception and feeding them directly into the reactive model predictive contouring control to adapt the safety conditions of the control barrier functions >

Taro: So, if perception is shaky, the control system automatically adjusts its safety margins online based on how uncertain it is about things >

Dev: Right. They have a pipeline that goes from environment perception to PKO Iterative Closest Point feature extraction and then kernel optimization and explainability before finally improving the control >

Rosa: It sounds like they're trying to make the system smarter about when it needs to be conservative versus when it can be efficient >

The paper's improvements: Dev: One key improvement mentioned is the active PKO via Concept Feedback mechanism which dynamically updates the tuner to a vector theta k that might include something like a correspondence gate or a robust loss scale >

Rosa: They only trigger this adaptation if necessary, specifically when they see concepts indicating why the estimate is uncertain, like when the dominant concept and or non-trivial uncertainty occur at most one tau on and the overall uncertainty is above some minimum threshold >

Taro: So it's not constantly changing things; it only adjusts when there's a specific reason to believe something is fuzzy, which sounds much more practical for real-time systems >

Dev: And they project these updated parameters onto the feasible set, which means whatever they change still has to stay within the limits of what the robot can safely do >

Rosa: Then there's this risk-aware control integration where the uncertainty modulates things like the contouring control barrier function relaxation, collision margins and desired speed >

Taro: So if that uncertainty spikes, it means they're going to automatically trade efficiency for conservatism by increasing slack penalties at high risk levels or reducing the desired speed >

Conclusion: Rosa: To wrap up this discussion on GUARD, the paper successfully combines traditional control with learning-driven perception to generate safe robot movements through uncertainty-aware ICP and risk-adaptive RMPCC >

Dev: It shows that by optimizing kernel parameters alongside uncertainty aware perception, they can derive a bounded risk measure rho k from concept posteriors and overall uncertainty using the formula clip zero one beta zero u k plus sigma c in C beta c pi k of c >

Taro: That risk measure essentially linearly inflates the margins and increases the slack penalty while reducing speed to tighten the safe set when uncertainty is high >

Rosa: And they flag out-of-distribution frames using a reject rule where if the overall uncertainty is above tau u or if the maximum concept posterior probability falls below tau p i, it triggers freezing kernel updates and reducing desired speed while inflating margins >

Dev: So, GUARD unifies reactive model predictive contouring control with uncertainty aware ICP to generate safe robot movements by adapting controller margins while preserving real-time performance >

Taro: It proves that this approach can adapt the controller settings to ensure safety without losing the real-time performance they need for sudden disturbances or obstacles >

Hertie Institute for Clinical Brain Research & Center for Integrative Neuroscience, University of Tubingen, Germany · Department of Intelligence and Information, Graduate School of Convergence Science and Technology, Seoul National University, Republic of Korea · Artificial Intelligence Institute (AIIS), Seoul National University, Republic of Korea · Department of Naval Architecture and Ocean Engineering, Seoul National University, Republic of Korea · School of Robotics, Kwangwoon University

cs.RO

Submitted: 2025-09-27

Updated: 2026-11-05

Comments: 9 pages, 9 figures, 2 tables. Substantially revised and expanded version with updated title and authors. Extended validation using model predictive control and reinforcement learning-based control

License: http://creativecommons.org/licenses/by-nc-sa/4.0/

Importance score: 87/100

The gist: This paper presents GUARD (Guided robot control via Uncertainty attribution and probabilistic kernel optimization for Risk-aware Decision making) that combines traditional control with an…

Key concepts

RMPCC
Reactive Model Predictive Contouring Control is a method that follows a desired path while ensuring safety constraints are met. It uses control barrier functions (CBFs) to guarantee collision avoidance and smooth evasive movements, operating in real-time at 100Hz.
ICP
Iterative Closest Point (ICP) is an algorithm used for point cloud registration, which aligns two sets of 3D points. GUARD uses ICP to estimate robot pose and simultaneously extracts uncertainty information about the alignment quality.
Probabilistic Kernel Optimization (PKO)
PKO adapts the robust kernel parameters in ICP by matching the observed data residuals with a model-based distribution. This makes ICP more robust against noise and partial overlaps, improving registration accuracy through iterative refinement.
Uncertainty Attribution
This process identifies *why* an estimate is uncertain by classifying it into specific concepts (like sensor noise or pose error) using a Gaussian Process Classifier. This allows the system to understand the source of uncertainty for better risk management.

Terminology

Summary

This paper presents GUARD (Guided robot control via Uncertainty attribution and probabilistic kernel optimization for Risk-aware Decision making) that combines traditional control with an uncertainty-aware perception technique using active learning with real-time capability for safe robot collision avoidance. p. 0

Where the paper says it

GUARD: Toward a Compromise between Traditional Control and Learning for Safe Robot Systems Johannes A. Gaus1 , Junheon Yoon2 , Woo-Jeong Baek3 , Seungwon Choi4 , Suhan Park5 , Jaeheung Park2 Abstract— This paper presents the framework GUARD (Guided robot control via Uncertainty attribution and probAbilistic kernel optimization for Risk-aware Decision making) that combines traditional control with an uncertaintyaware perception technique using active learning with realtime capability for safe robot collision avoidance.

By doing so, this manuscript addresses the central challenge in robotics of finding a reasonable compromise between traditional methods and learning algorithms to foster the development of safe, yet efficient and flexible applications. p. 0
Where the paper says it

Gaus1 , Junheon Yoon2 , Woo-Jeong Baek3 , Seungwon Choi4 , Suhan Park5 , Jaeheung Park2 Abstract— This paper presents the framework GUARD (Guided robot control via Uncertainty attribution and probAbilistic kernel optimization for Risk-aware Decision making) that combines traditional control with an uncertaintyaware perception technique using active learning with realtime capability for safe robot collision avoidance. By doing so, this manuscript addresses the central challenge in robotics of finding a reasonable compromise between traditional methods and learning algorithms to foster the development of safe, yet efficient and flexible applications.

p. 0
Where the paper says it

Gaus1 , Junheon Yoon2 , Woo-Jeong Baek3 , Seungwon Choi4 , Suhan Park5 , Jaeheung Park2 Abstract— This paper presents the framework GUARD (Guided robot control via Uncertainty attribution and probAbilistic kernel optimization for Risk-aware Decision making) that combines traditional control with an uncertaintyaware perception technique using active learning with realtime capability for safe robot collision avoidance. By doing so, this manuscript addresses the central challenge in robotics of finding a reasonable compromise between traditional methods and learning algorithms to foster the development of safe, yet efficient and flexible applications.

The core idea is that safety is evaluated inversely by the uncertainty. p. 0
Where the paper says it

For example, it remains unclear how the perception parameters affect the robot control performance in the context of safety. To complement traditional techniques with learning in a safe and efficient manner, this paper contends that safety is evaluated inversely by the uncertainty.

Framework Components

The GUARD framework unifies reactive model predictive contouring control (RMPCC) with an Iterative Closest Point (ICP) algorithm that enables the attribution of uncertainty sources online using active learning with real-time capability via a probabilistic kernel optimization technique. This unification adapts the safety conditions of the CBFs in the RMPCC by referring to the perception uncertainties. p. 0

Where the paper says it

By further actively adapting the kernel parameters via our previous work in [5], robustness is achieved. This unification adapts the safety conditions of the CBFs in the RMPCC by referring to the perception uncertainties.

p. 0
Where the paper says it

By further actively adapting the kernel parameters via our previous work in [5], robustness is achieved. This unification adapts the safety conditions of the CBFs in the RMPCC by referring to the perception uncertainties.

The pipeline involves Env. p. 2
Where the paper says it

THE FRAMEWORK GUARD This section presents GUARD (Guided robot control via Uncertainty attribution and probAbilistic kernel optimization for Risk-aware Decision making) by combining and extending methods from prior works for safe robot systems. The following steps, illustrated in the figure 3, outline the complete GUARD pipeline: - Env.

Perception, PKO–ICP, Feature extraction from ICP, Kernel Optimization, Explainability, and Improved Control. p. 2
Where the paper says it

The computation O(|C|d) is negligible compared to ICP and feature extraction. Uncertainty-aware Robot Control This section integrates the perception module into the RMPCC to relax the assumption on the perfectly accurate perception in [4].

Active Adaptation Mechanism

The active PKO via Concept Feedback mechanism dynamically updates the tuner to a vector θk that may include a correspondence gate or robust-loss scale. The adaptation is triggered only if necessary via the concepts that indicate why the estimate is uncertain, specifically when dominant concept and/or non-trivial uncertainty occur (maxc πk(c) ≥ τon and uk ≥ umin). The updated parameters are projected onto the feasible set Θ. p. 2

Where the paper says it

GUARD selects the exact schedules empirically. The updated parameters are projected onto the feasible set Θ: θk+1 = ΠΘ θk + ∆θk .

Risk-Aware Control Integration

The uncertainty-aware robot control integrates perception into RMPCC to relax the assumption on perfectly accurate perception. The scalar risk and per-concept posteriors modulate (i)the CBF relaxation (large slack penalties at high risk), (ii)collision margins and desired speed vdes, and (iii)soft weights wc,wl,wo,wvs to trade efficiency for conservatism if perception uncertainty spikes. p. 2

Where the paper says it

Uncertainty-aware Robot Control This section integrates the perception module into the RMPCC to relax the assumption on the perfectly accurate perception in [4]. Since uncertainties are proportional to risks, the perception uncertainty enables to develop riskaware robot controllers: The scalar risk and per-concept posteriors modulate (i)the CBF relaxation (large slack penalties at high risk), (ii)collision margins and desired speed vdes, and (iii)soft weights wc,wl ,wo,wvs to trade efficiency for conservatism if perception uncertainty spikes.

This results in the scalar risk ρk being calculated as clip[0,1]β0 uk + X c∈C βc πk(c). p. 3
Where the paper says it

The controller becomes conservative for high uncertainties. Calibrated concept posteriors πk(c) and entropy uk yield ρk = clip[0,1] β0 uk + X c∈C βc πk(c) , (8) where β ≥0 weight each source.

Experimental Validation

Experiments evaluate standard point-to-plane ICP, Stein-ICP, and PKO-ICP on synthetic benchmarks like HELIX, TORUS, and KNOT. PKO-ICP shows a promising accuracy–latency trade-off compared to standard ICP. p. 2

Where the paper says it

PKO-ICP attains a promising accuracy–latency trade-off, see Tab. I: Standard ICP runs at ∼0.

Furthermore, GUARD flags out-of-distribution frames using a reject rule based on calibrated uncertainty. p. 3
Where the paper says it

OOD Robustness. GUARD flags out-of-distribution frames using a reject rule on the calibrated uncertainty: OODk = 1 h uk > τu ∨ max c∈C πk(c) < τp i .

Conclusion

GUARD unifies traditional control RMPCC with learning-driven perception to generate safe robot movements. The framework successfully combines the optimization of kernel parameters with uncertainty-aware perception to generate safe robot movements. p. 3

Where the paper says it

CONCLUSION This paper presented GUARD that unifies traditional control RMPCC in [4] with learning-driven perception. GUARD combines the optimization of kernel parameters with uncertainty-aware perception to generate safe robot movements.

Experimental results demonstrate the performance and reliability of GUARD. p. 3
Where the paper says it

The attributed risk adapts controller margins, yielding safety while preserving real-time performance. Experimental results demonstrate the performance and reliability of GUARD.

The paper concludes that this approach adapts controller margins, yielding safety while preserving real-time performance. p. 3
Where the paper says it

GUARD combines the optimization of kernel parameters with uncertainty-aware perception to generate safe robot movements. The attributed risk adapts controller margins, yielding safety while preserving real-time performance.

--- Page 1 ---

GUARD: Toward a Compromise between Traditional Control and Learning for Safe Robot Systems Johannes A. Gaus1, Junheon Yoon2, Woo-Jeong Baek3, Seungwon Choi4, Suhan Park5, Jaeheung Park2 Abstract— This paper presents the framework GUARD (Guided robot control via Uncertainty attribution and probAbilistic kernel optimization for Risk-aware Decision making) that combines traditional control with an uncertaintyaware perception technique using active learning with realtime capability for safe robot collision avoidance. p. 0

Where the paper says it

GUARD: Toward a Compromise between Traditional Control and Learning for Safe Robot Systems Johannes A. Gaus1 , Junheon Yoon2 , Woo-Jeong Baek3 , Seungwon Choi4 , Suhan Park5 , Jaeheung Park2 Abstract— This paper presents the framework GUARD (Guided robot control via Uncertainty attribution and probAbilistic kernel optimization for Risk-aware Decision making) that combines traditional control with an uncertaintyaware perception technique using active learning with realtime capability for safe robot collision avoidance.

By doing so, this manuscript addresses the central challenge in robotics of finding a reasonable compromise between traditional methods and learning algorithms to foster the development of safe, yet efficient and flexible applications. By unifying a reactive model predictive contouring control (RMPCC) with an Iterative Closest Point (ICP) algorithm that enables the attribution of uncertainty sources online using active learning with real-time capability via a probabilistic kernel optimization technique, GUARD inherently handles the existing ambiguity of the term safety that exists in robotics literature. p. 0
Where the paper says it

By doing so, this manuscript addresses the central challenge in robotics of finding a reasonable compromise between traditional methods and learning algorithms to foster the development of safe, yet efficient and flexible applications. By unifying a reactive model predictive countouring control (RMPCC) with an Iterative Closest Point (ICP) algorithm that enables the attribution of uncertainty sources online using active learning with real-time capability via a probabilistic kernel optimization technique, GUARD inherently handles the existing ambiguity of the term safety that exists in robotics literature.

Experimental studies indicate the high performance of GUARD, thereby highlighting the relevance and need to broaden its applicability in future. p. 0
Where the paper says it

By unifying a reactive model predictive countouring control (RMPCC) with an Iterative Closest Point (ICP) algorithm that enables the attribution of uncertainty sources online using active learning with real-time capability via a probabilistic kernel optimization technique, GUARD inherently handles the existing ambiguity of the term safety that exists in robotics literature. Experimental studies indicate the high performance of GUARD, thereby highlighting the relevance and need to broaden its applicability in future.

I. INTRODUCTION Developing safe and flexible robot applications is a central, yet open issue in robotics. p. 0
Where the paper says it

Experimental studies indicate the high performance of GUARD, thereby highlighting the relevance and need to broaden its applicability in future. INTRODUCTION Developing safe and flexible robot applications is a central, yet open issue in robotics.

One major difficulty arises due to the challenge to develop systems that are sufficiently explainable to verify safety, and enable the use of efficient learning methods. p. 0
Where the paper says it

INTRODUCTION Developing safe and flexible robot applications is a central, yet open issue in robotics. One major difficulty arises due to the challenge to develop systems that are sufficiently explainable to verify safety, and enable the use of efficient learning methods.

Thus, a suitable compromise must be found such that safety, that requires explainability, can be evaluated while preserving the benefits of learning. p. 0
Where the paper says it

One major difficulty arises due to the challenge to develop systems that are sufficiently explainable to verify safety, and enable the use of efficient learning methods. Thus, a suitable compromise must be found such that safety, that requires explainability, can be evaluated while preserving the benefits of learning.

While end-to-end learning like in ([1], [2], [3]) have led to promising results regarding their efficiency, their black-box character causes a burden on assessing safety. p. 0
Where the paper says it

Thus, a suitable compromise must be found such that safety, that requires explainability, can be evaluated while preserving the benefits of learning. While end-to-end learning like in ( [1], [2], [3]) have led to promising results regarding their efficiency, their black-box character causes a burden on assessing safety.

A second challenge lies in the ambiguity of the safety definitions in the different subdomains. p. 0
Where the paper says it

While end-to-end learning like in ( [1], [2], [3]) have led to promising results regarding their efficiency, their black-box character causes a burden on assessing safety. A second challenge lies in the ambiguity of the safety definitions in the different subdomains.

Robotic systems employ methods from control, perception, and/or state estimation. p. 0
Where the paper says it

A second challenge lies in the ambiguity of the safety definitions in the different subdomains. Robotic systems employ methods from control, perception, and/or state estimation.

Especially, the respective assumptions that must be met (e. p. 0
Where the paper says it

Robotic systems employ methods from control, perception, and/or state estimation. Especially, the respective assumptions that must be met (e.

g., control barrier functions (CBFs) in traditional control, registration accuracy in perception, etc. p. 0
Where the paper says it

Especially, the respective assumptions that must be met (e. , control barrier functions (CBFs) in traditional control, registration accuracy in perception,.

) are formulated in a domain-specific manner. p. 0
Where the paper says it

, control barrier functions (CBFs) in traditional control, registration accuracy in perception,. ) are formulated in a domain-specific manner.

However, the relationship between these requirements is often not known. p. 0
Where the paper says it

) are formulated in a domain-specific manner. However, the relationship between these requirements is often not known.

For example, it remains unclear how the perception parameters affect the robot control performance in the context of safety. p. 0
Where the paper says it

However, the relationship between these requirements is often not known. For example, it remains unclear how the perception parameters affect the robot control performance in the context of safety.

To complement traditional techniques with learning in a safe and efficient manner, this paper contends that safety is evaluated inversely by the uncertainty. p. 0
Where the paper says it

For example, it remains unclear how the perception parameters affect the robot control performance in the context of safety. To complement traditional techniques with learning in a safe and efficient manner, this paper contends that safety is evaluated inversely by the uncertainty.

1 Hertie Institute for Clinical Brain Research & Center for Integrative Neuroscience, University of Tubingen, Germany. p. 0
Where the paper says it

To complement traditional techniques with learning in a safe and efficient manner, this paper contends that safety is evaluated inversely by the uncertainty. 1 Hertie Institute for Clinical Brain Research & Center for Integrative Neuroscience, University of Tubingen, Germany.

2 Department of Intelligence and Information, Graduate School of Convergence Science and Technology, Seoul National University, Republic of Korea. p. 0
Where the paper says it

1 Hertie Institute for Clinical Brain Research & Center for Integrative Neuroscience, University of Tubingen, Germany. ¨ 2 Department of Intelligence and Information, Graduate School of Convergence Science and Technology, Seoul National University, Republic of Korea.

3 Artificial Intelligence Institute (AIIS), Seoul National University, Republic of Korea. p. 0
Where the paper says it

¨ 2 Department of Intelligence and Information, Graduate School of Convergence Science and Technology, Seoul National University, Republic of Korea. 3 Artificial Intelligence Institute (AIIS), Seoul National University, Republic of Korea.

4 Department of Naval Architecture and Ocean Engineering, Seoul National University, Republic of Korea. p. 0
Where the paper says it

3 Artificial Intelligence Institute (AIIS), Seoul National University, Republic of Korea. 4 Department of Naval Architecture and Ocean Engineering, Seoul National University, Republic of Korea.

5 School of Robotics, Kwangwoon University, Seoul, Republic of Korea. p. 0
Where the paper says it

4 Department of Naval Architecture and Ocean Engineering, Seoul National University, Republic of Korea. 5 School of Robotics, Kwangwoon University, Seoul, Republic of Korea.

Thus, the uncertainty is treated as the key measure for safety evaluation. p. 0
Where the paper says it

5 School of Robotics, Kwangwoon University, Seoul, Republic of Korea. Thus, the uncertainty is treated as the key measure for safety evaluation.

The uncertainty reflects the possible deviation of a quantity and is expressed as a probability. p. 0
Where the paper says it

Thus, the uncertainty is treated as the key measure for safety evaluation. The uncertainty reflects the possible deviation of a quantity and is expressed as a probability.

Logically, the absence of uncertainties (uncertainty = 0) ensures safety: In case all system variables are known with perfect accuracy at each time step, dangerous situations can be avoided by introducing risk-avoiding measures in time. p. 0
Where the paper says it

The uncertainty reflects the possible deviation of a quantity and is expressed as a probability. Logically, the absence of uncertainties (uncertainty = 0) ensures safety: In case all system variables are known with perfect accuracy at each time step, dangerous situations can be avoided by introducing risk-avoiding measures in time.

This paper suggests GUARD to combine reactive model predictive contouring control (RMPCC) from prior work in [4] that ensures smooth evasive movements with uncertainty-aware ICP. p. 0
Where the paper says it

Logically, the absence of uncertainties (uncertainty = 0) ensures safety: In case all system variables are known with perfect accuracy at each time step, dangerous situations can be avoided by introducing risk-avoiding measures in time. This paper suggests GUARD to combine reactive model predictive contouring control (RMPCC) from prior work in [4] that ensures smooth evasive movements with uncertainty-aware ICP.

By further actively adapting the kernel parameters via our previous work in [5], robustness is achieved. p. 0
Where the paper says it

This paper suggests GUARD to combine reactive model predictive contouring control (RMPCC) from prior work in [4] that ensures smooth evasive movements with uncertainty-aware ICP. By further actively adapting the kernel parameters via our previous work in [5], robustness is achieved.

This unification adapts the safety conditions of the CBFs in the RMPCC by referring to the perception uncertainties. Practically, more conservative robot movements are generated in case of high perception uncertainties while maximizing the efficiency for negligible uncertainties. p. 0
Where the paper says it

This unification adapts the safety conditions of the CBFs in the RMPCC by referring to the perception uncertainties. Practically, more conservative robot movements are generated in case of high perception uncertainties while maximizing the efficiency for negligible uncertainties.

The real-time capability (100Hz) enables to handle sudden occurrence of obstacles or unexpected disturbances. p. 0
Where the paper says it

Practically, more conservative robot movements are generated in case of high perception uncertainties while maximizing the efficiency for negligible uncertainties. The real-time capability (100Hz) enables to handle sudden occurrence of obstacles or unexpected disturbances.

a) Related Work: Classical path following can be split into time–parameterized planners/trackers and path–parameterized MPC. p. 0
Where the paper says it

The real-time capability (100Hz) enables to handle sudden occurrence of obstacles or unexpected disturbances. a) Related Work: Classical path following can be split into time–parameterized planners/trackers and path–parameterized MPC.

The former optimize a time–indexed trajectory that a low–level controller tracks [6]–[11]; the latter optimizes progress along a spatial path to gain temporal flexibility and real-time reactivity evaluated on cars, UAVs, and manipulators [12], [13]. p. 0
Where the paper says it

a) Related Work: Classical path following can be split into time–parameterized planners/trackers and path–parameterized MPC. The former optimize a time–indexed trajectory that a low–level controller tracks [6]–[11]; the latter optimizes progress along a spatial path to gain temporal flexibility and real–time reactivity evaluated on cars, UAVs, and manipulators [12], [13].

For safety, artificial potential fields have been widely used, while CBFs yield forward-invariance guarantees and typically less intrusive avoidance [14], [15]. p. 0
Where the paper says it

The former optimize a time–indexed trajectory that a low–level controller tracks [6]–[11]; the latter optimizes progress along a spatial path to gain temporal flexibility and real–time reactivity evaluated on cars, UAVs, and manipulators [12], [13]. For safety, artificial potential fields have been widely used, while CBFs yield forward–invariance guarantees and typically less intrusive avoidance [14], [15].

RMPCC combines path–parameterized MPC with CBFs and achieves high servo rates via Jacobian linearization and Gauss–Newton/SQP [4]. p. 0
Where the paper says it

For safety, artificial potential fields have been widely used, while CBFs yield forward–invariance guarantees and typically less intrusive avoidance [14], [15]. RMPCC combines path–parameterized MPC with CBFs and achieves high servo rates via Jacobian linearization and Gauss–Newton/SQP [4].

On the perception side, ICP remains the workhorse for point-cloud registration [16], [17]. p. 0
Where the paper says it

RMPCC combines path–parameterized MPC with CBFs and achieves high servo rates via Jacobian linearization and Gauss–Newton/SQP [4]. On the perception side, ICP remains the workhorse for point–cloud registration [16], [17].

Uncertainty has been analyzed via closed-form covariances [18] and their limitations [19], learned covariance predictors (CELLO-3D) [20], and probabilistic/multi-modal variants (e. p. 0
Where the paper says it

On the perception side, ICP remains the workhorse for point–cloud registration [16], [17]. Uncertainty has been analyzed via closed-form covariances [18] and their limitations [19], learned covariance predictors (CELLO-3D) [20], and probabilistic/multi-modal variants (e.

g., Stein-ICP) [21]. p. 0
Where the paper says it

Uncertainty has been analyzed via closed-form covariances [18] and their limitations [19], learned covariance predictors (CELLO-3D) [20], and probabilistic/multi-modal variants (e. , Stein-ICP) [21].

However, most pipelines quantify how much uncertainty exists but not why. p. 0
Where the paper says it

, Stein-ICP) [21]. However, most pipelines quantify how much uncertainty exists but not why.

Concept-based explanations as TCAV with point-cloud encoders (PointNet/DGCNN) [23], [24] enable human-interpretable attribution. p. 0
Where the paper says it

However, most pipelines quantify how much uncertainty exists but not why. Concept-based explanations as TCAV [22] with point-cloud encoders (PointNet/DGCNN) [23], [24] enable human-interpretable attribution.

Recent post-hoc attribution for ICP exists but is computationally heavy and not integrated with control [25]. p. 0
Where the paper says it

Concept-based explanations as TCAV [22] with point-cloud encoders (PointNet/DGCNN) [23], [24] enable human-interpretable attribution. Recent post-hoc attribution for ICP exists but is computationally heavy and not integrated with control [25].

Probabilistic Kernel Optimization (PKO) adapts robust kernels by matching model/data inlier distributions to improve registration robustness [5]. p. 0
Where the paper says it

Recent post-hoc attribution for ICP exists but is computationally heavy and not integrated with control [25]. Probabilistic Kernel Optimization (PKO) adapts robust kernels by matching model/data inlier distributions to improve registration robustness [5].

Contribution. p. 0
Where the paper says it

Probabilistic Kernel Optimization (PKO) adapts robust kernels by matching model/data inlier distributions to improve registration robustness [5]. Contribution.

GUARD differs by (i) attaching per-concept, calibrated attributions to ICP uncertainty and (ii) feeding these uncertainties into RMPCC to adapt safety margins online while preserving real-time performance, bridging perception failures to control guarantees. p. 0
Where the paper says it

Contribution. GUARD differs by (i) attaching per-concept, calibrated attributions to ICP uncertainty and (ii) feeding these uncertainties into RMPCC to adapt safety margins arXiv:2509. p. 0

Where the paper says it

Contribution. GUARD differs by (i) attaching per-concept, calibrated attributions to ICP uncertainty and (ii) feeding these uncertainties into RMPCC to adapt safety margins arXiv:2509.

arXiv:2509.23312v1 [cs. p. 0
Where the paper says it

GUARD differs by (i) attaching per-concept, calibrated attributions to ICP uncertainty and (ii) feeding these uncertainties into RMPCC to adapt safety margins arXiv:2509. 23312v1 [cs.

RO] 27 Sep 2025

--- Page 2 ---

online while preserving real-time performance, bridging perception failures to control guarantees. II. PRELIMINARIES AND PRIOR WORK Iterative Closest Point (ICP) Algorithm ICP estimates the rigid motion T = (R, t) ∈ SE(3) that aligns a source point cloud to a target cloud by alternating correspondence assignment and a small weighted least-squares update. p. 1

Where the paper says it

online while preserving real-time performance, bridging perception failures to control guarantees. PRELIMINARIES AND PRIOR WORK Iterative Closest Point (ICP) Algorithm ICP estimates the rigid motion T = (R, t) ∈ SE(3) that aligns a source point cloud to a target cloud by alternating correspondence assignment and a small weighted least-squares update.

In the point-to-plane variant [16], each iteration minimizes residuals of the form ri = n⊤i Rpi + t − qi. p. 1
Where the paper says it

PRELIMINARIES AND PRIOR WORK Iterative Closest Point (ICP) Algorithm ICP estimates the rigid motion T = (R, t) ∈ SE(3) that aligns a source point cloud to a target cloud by alternating correspondence assignment and a small weighted least-squares update. In the point-to-plane variant [16], each iteration minimizes residuals of the form ri = n ⊤ i Rpi + t − qi .

The per-iteration residual set, inlier counts, and overlap proxies provide both the pose estimate and rich cues about the scene (e. p. 1
Where the paper says it

In the point-to-plane variant [16], each iteration minimizes residuals of the form ri = n ⊤ i Rpi + t − qi . The per-iteration residual set {ri}, inlier counts, and overlap proxies provide both the pose estimate and rich cues about the scene (e.

g., occlusion, poor overlap, dynamic objects). p. 1
Where the paper says it

The per-iteration residual set {ri}, inlier counts, and overlap proxies provide both the pose estimate and rich cues about the scene (e. , occlusion, poor overlap, dynamic objects).

Probabilistic Kernel Optimization (PKO) Our previous work [5] uses above residuals to adapt the robust kernel parameters by matching an inlier distribution with the empirical residual. p. 1
Where the paper says it

, occlusion, poor overlap, dynamic objects). Probabilistic Kernel Optimization (PKO) Our previous work [5] uses above residuals to adapt the robust kernel parameters by matching an inlier distribution with the empirical residual.

To be specific, PKO refers to the iteratively reweighted least squares (IRLS) algorithm that employs a weighting scheme for the residuals by assigning smaller weights to outliers, thereby minimizing their influence on the optimization. p. 1
Where the paper says it

Probabilistic Kernel Optimization (PKO) Our previous work [5] uses above residuals to adapt the robust kernel parameters by matching an inlier distribution with the empirical residual. To be specific, PKO refers to the iteratively reweighted least squares (IRLS) algorithm that employs a weighting scheme for the residuals by assigning smaller weights to outliers, thereby minimizing their influence on the optimization.

PKO enhances the robustness as follows: For the IRLS weight w(r; c) with the scaling parameter c of the robust kernel, a model-based inlier probability Pmodel(inlier r, c) = w(r; c)/Zw, and a data-based inlier probability Pdata(inlier r) from a short window of recent residual magnitudes is defined. p. 1
Where the paper says it

To be specific, PKO refers to the iteratively reweighted least squares (IRLS) algorithm that employs a weighting scheme for the residuals by assigning smaller weights to outliers, thereby minimizing their influence on the optimization. PKO enhances the robustness as follows: For the IRLS weight w(r; c) with the scaling parameter c of the robust kernel, a model-based inlier probability Pmodel(inlier | r, c) = w(r; c)/Zw, and a data-based inlier probability Pdata(inlier | r) from a short window of recent residual magnitudes is defined.

At each IRLS iteration, c is adapted via the Jensen-Shannon divergence JS: c⋆ = argmin c JS Pdata(·)∥ Pmodel(· c). p. 1
Where the paper says it

PKO enhances the robustness as follows: For the IRLS weight w(r; c) with the scaling parameter c of the robust kernel, a model-based inlier probability Pmodel(inlier | r, c) = w(r; c)/Zw, and a data-based inlier probability Pdata(inlier | r) from a short window of recent residual magnitudes is defined. At each IRLS iteration, c is adapted via the Jensen-Shannon divergence JS: c ⋆ = argmin c JS Pdata(·) ∥ Pmodel(· | c) .

This aligns the effective inlier boundary with the sensor data reflecting the actual state. p. 1
Where the paper says it

At each IRLS iteration, c is adapted via the Jensen-Shannon divergence JS: c ⋆ = argmin c JS Pdata(·) ∥ Pmodel(· | c) . This aligns the effective inlier boundary with the sensor data reflecting the actual state.

With the improving alignment, c⋆ decreases, reproducing a graduated-nonconvexity behavior. p. 1
Where the paper says it

This aligns the effective inlier boundary with the sensor data reflecting the actual state. With the improving alignment, c ⋆ decreases, reproducing a graduated-nonconvexity behavior.

PKO improves the tolerance against initialization uncertainties, sensor noise and partial overlaps. p. 1
Where the paper says it

With the improving alignment, c ⋆ decreases, reproducing a graduated-nonconvexity behavior. PKO improves the tolerance against initialization uncertainties, sensor noise and partial overlaps.

TCAV–GPC for uncertainty attribution for ICP The lack of interpretability in residual-driven adaptation is addressed by integrating the technique of Testing with Concept Activation Vectors (TCAV) [22]. p. 1
Where the paper says it

PKO improves the tolerance against initialization uncertainties, sensor noise and partial overlaps. TCAV–GPC for uncertainty attribution for ICP The lack of interpretability in residual-driven adaptation is addressed by integrating the technique of Testing with Concept Activation Vectors (TCAV) [22].

The perception is performed via RGB-D frames that are processed with ICP. p. 1
Where the paper says it

TCAV–GPC for uncertainty attribution for ICP The lack of interpretability in residual-driven adaptation is addressed by integrating the technique of Testing with Concept Activation Vectors (TCAV) [22]. The perception is performed via RGB-D frames that are processed with ICP.

With the obtained point clouds, TCAV extracts expressive features via a pretrained model like Dynamic Graph CNN (DGCNN) or a PointNet approach [23], [24]. p. 1
Where the paper says it

The perception is performed via RGB-D frames that are processed with ICP. With the obtained point clouds, TCAV extracts expressive features via a pretrained model like Dynamic Graph CNN (DGCNN) or a PointNet approach [23], [24].

For the embedding ek = fθ(Pk) generated by the encoder corresponding to the point cloud Pk, a feature vector ϕk = ek] ∈ R d is formed. p. 1
Where the paper says it

With the obtained point clouds, TCAV extracts expressive features via a pretrained model like Dynamic Graph CNN (DGCNN) or a PointNet approach [23], [24]. For the embedding ek = fθ(Pk) generated by the encoder corresponding to the point cloud Pk, a feature vector ϕk = ek ] ∈ R d is formed.

By training a multi-class Gaussian Process Classifier (GPC) with these vectors on artificially perturbed data, the goal is to classify ϕk in three semantic uncertainty concepts C = [sensor noise, pose error, partial overlap]. p. 1
Where the paper says it

For the embedding ek = fθ(Pk) generated by the encoder corresponding to the point cloud Pk, a feature vector ϕk = ek ] ∈ R d is formed. By training a multi-class Gaussian Process Classifier (GPC) with these vectors on artificially perturbed data, the goal is to classify ϕk in three semantic uncertainty concepts C = {sensor noise, pose error, partial overlap}.

At test time the GPC yields calibrated posteriors πk(c) = p(c ϕk,D), c ∈ C,uk = − X c∈C πk(c)logπk(c), where uk summarizes overall predictive uncertainty. p. 1
Where the paper says it

By training a multi-class Gaussian Process Classifier (GPC) with these vectors on artificially perturbed data, the goal is to classify ϕk in three semantic uncertainty concepts C = {sensor noise, pose error, partial overlap}. At test time the GPC yields calibrated posteriors πk(c) = p(c |ϕk ,D), c ∈ C,uk = − X c∈C πk(c)logπk(c), where uk summarizes overall predictive uncertainty.

In practice, πk(c) is computed via a standard multi-class GP link with a Laplace approximation or Monte Carlo samples of the latent scores. p. 1
Where the paper says it

At test time the GPC yields calibrated posteriors πk(c) = p(c |ϕk ,D), c ∈ C,uk = − X c∈C πk(c)logπk(c), where uk summarizes overall predictive uncertainty. In practice, πk(c) is computed via a standard multi-class GP link with a Laplace approximation or Monte Carlo samples of the latent scores.

Sampling from the GPC posterior provides both per-concept attribution scores and calibrated uncertainty estimates uk. p. 1
Where the paper says it

In practice, πk(c) is computed via a standard multi-class GP link with a Laplace approximation or Monte Carlo samples of the latent scores. Sampling from the GPC posterior provides both per-concept attribution scores {πk(c)}c∈C and calibrated uncertainty estimates uk.

This analysis inspired by TCAV in [22] in the encoder space provides sc(ek) = ∇e gc(e)⊤ e=ek vc, where gc is the pre-link class score and vc is the concept activation vector for concept c. p. 1
Where the paper says it

Sampling from the GPC posterior provides both per-concept attribution scores {πk(c)}c∈C and calibrated uncertainty estimates uk. This analysis inspired by TCAV in [22] in the encoder space provides sc(ek) = ∇e gc(e) ⊤ e=ek vc, where gc is the pre-link class score and vc is the concept activation vector for concept c.

This enables the system both to measure how uncertain a registration is (uk) and to explain why (via the dominant concept c⋆ k = argmaxc πk(c). p. 1
Where the paper says it

This analysis inspired by TCAV in [22] in the encoder space provides sc(ek) = ∇e gc(e) ⊤ e=ek vc, where gc is the pre-link class score and vc is the concept activation vector for concept c. This enables the system both to measure how uncertain a registration is (uk) and to explain why (via the dominant concept c ⋆ k = argmaxc πk(c)).

--- Page 3 ---

Fig. 2: Schematic description of GUARD. p. 2

Where the paper says it

2: Schematic description of GUARD. 3: Overview of GUARD: concept-attributed perception drives risk-adaptive RMPCC in real time.

Fig. 3: Overview of GUARD: concept-attributed perception drives risk-adaptive RMPCC in real time. p. 2
Where the paper says it

2: Schematic description of GUARD. 3: Overview of GUARD: concept-attributed perception drives risk-adaptive RMPCC in real time.

Reactive Model Predictive Contouring Control (RMPCC Our prior work [4] presents RMPCC shown in Figure 1 that follows a reference path with CBFs. p. 1

Where the paper says it

Assuming a perfectly accurate perception, RMPCC proposes a controller that considers CBF constraints. Reactive Model Predictive Contouring Control (RMPCC) Our prior work [4] presents RMPCC shown in Figure 1 that follows a reference path with CBFs.

The robot path is parameterized by a path parameter s ∈ [0,1], formalized via a position spline pr(s) ∈ R 3 and an orientation curve Rr(s) ∈ SO(3). p. 1
Where the paper says it

Reactive Model Predictive Contouring Control (RMPCC) Our prior work [4] presents RMPCC shown in Figure 1 that follows a reference path with CBFs. The robot path is parameterized by a path parameter s ∈ [0,1], formalized via a position spline pr(s) ∈ R 3 and an orientation curve Rr(s) ∈ SO(3).

For the robot joint configuration q ∈ R n, the end-effector pose pee(q) and Ree(q), RMPCC refers to a surrogate path–progress state (s,vs) with discrete dynamics. p. 1
Where the paper says it

The robot path is parameterized by a path parameter s ∈ [0,1], formalized via a position spline pr(s) ∈ R 3 and an orientation curve Rr(s) ∈ SO(3). For the robot joint configuration q ∈ R n, the end-effector pose pee(q) and Ree(q), RMPCC refers to a surrogate path–progress state (s,vs) with discrete dynamics.

For the robot state and control input xk = q⊤k sk vs,k⊤, uk = q˙⊤k v˙s,k⊤. p. 1
Where the paper says it

For the robot joint configuration q ∈ R n, the end-effector pose pee(q) and Ree(q), RMPCC refers to a surrogate path–progress state (s,vs) with discrete dynamics. For the robot state and control input xk = q ⊤ k sk vs,k⊤ , uk = q˙ ⊤ k v˙s,k⊤ , the controller minimizes tracking error and control effort over a horizon N: J = Lf (xN ) + N X−1 k=1 L(xk,uk,uk−1), (1) with stage cost L = wc∥ec∥ 2 + wl∥el∥ 2 + wvs (vdes − vs,k) 2 | {z } tracking +wo∥Log(R ⊤ r Ree)∥ 2 | {z } orientation +wq˙∥q˙k∥ 2 + w∆ ˙q∥∆ ˙qk∥ 2 + wv˙s v˙ 2 s,k | {z } regularization , (2) Here, e = pr(sk) − pee(qk) is split into contouring and lag error using the local path tangent, ∆ ˙qk = ˙qk − q˙k−1 (with ∆ ˙q1 = 0), and Log(·) denotes the matrix logarithm on SO(3).

The controller minimizes tracking error and control effort over a horizon N: J = Lf (xN) + N X−1 k=1 L(xk,uk,uk−1), with stage cost L = wc∥ec∥2 + wl∥el∥2 + wvs (vdes − vs,k)2 tracking + woLog(R⊤r Ree) squared orientation + wq˙q˙k squared + w∆ ˙q∆ ˙qk squared regularization, and wv˙s v˙s k squared s,k regularization. p. 1
Where the paper says it

For the robot joint configuration q ∈ R n, the end-effector pose pee(q) and Ree(q), RMPCC refers to a surrogate path–progress state (s,vs) with discrete dynamics. For the robot state and control input xk = q ⊤ k sk vs,k⊤ , uk = q˙ ⊤ k v˙s,k⊤ , the controller minimizes tracking error and control effort over a horizon N: J = Lf (xN ) + N X−1 k=1 L(xk,uk,uk−1), (1) with stage cost L = wc∥ec∥ 2 + wl∥el∥ 2 + wvs (vdes − vs,k) 2 | {z } tracking +wo∥Log(R ⊤ r Ree)∥ 2 | {z } orientation +wq˙∥q˙k∥ 2 + w∆ ˙q∥∆ ˙qk∥ 2 + wv˙s v˙ 2 s,k | {z } regularization , (2) Here, e = pr(sk) − pee(qk) is split into contouring and lag error using the local path tangent, ∆ ˙qk = ˙qk − q˙k−1 (with ∆ ˙q1 = 0), and Log(·) denotes the matrix logarithm on SO(3).

Safety is considered via CBFs on (i) kinematic singularities, (ii) self–collision, and (iii) environment collision. p. 1
Where the paper says it

For the robot state and control input xk = q ⊤ k sk vs,k⊤ , uk = q˙ ⊤ k v˙s,k⊤ , the controller minimizes tracking error and control effort over a horizon N: J = Lf (xN ) + N X−1 k=1 L(xk,uk,uk−1), (1) with stage cost L = wc∥ec∥ 2 + wl∥el∥ 2 + wvs (vdes − vs,k) 2 | {z } tracking +wo∥Log(R ⊤ r Ree)∥ 2 | {z } orientation +wq˙∥q˙k∥ 2 + w∆ ˙q∥∆ ˙qk∥ 2 + wv˙s v˙ 2 s,k | {z } regularization , (2) Here, e = pr(sk) − pee(qk) is split into contouring and lag error using the local path tangent, ∆ ˙qk = ˙qk − q˙k−1 (with ∆ ˙q1 = 0), and Log(·) denotes the matrix logarithm on SO(3). Safety is considered via CBFs on (i) kinematic singularities, (ii) self–collision, and (iii) environment collision.

The algorithm proposes barrier functions h(q) ≥ 0 hsing(q) = µ(q) − εsing, µ(q) = q detJee(q)Jee(q)⊤, hself(q)= dself(q)- εself. p. 1
Where the paper says it

Safety is considered via CBFs on (i) kinematic singularities, (ii) self–collision, and (iii) environment collision. The algorithm proposes barrier functions h(q) ≥ 0 hsing(q) = µ(q) − εsing, (3) µ(q) = q detJee(q)Jee(q)⊤ , (4) hself(q) = dself(q) − εself.

henv,l (q, pobs)= denv,l (q, pobs) − robs - εenv for each link l. p. 2
Where the paper says it

3: Overview of GUARD: concept-attributed perception drives risk-adaptive RMPCC in real time. and henv,ℓ(q, pobs) = denv,ℓ(q, pobs) − robs − εenv for each link ℓ.

Here, Jee denotes the end-effector Jacobian; dself and denv,l are the minimum distances to self-collision and to the l-th robot link’s collision with the obstacle as predicted by a deep neural network; and ε· > 0 denote safety margins. p. 2
Where the paper says it

and henv,ℓ(q, pobs) = denv,ℓ(q, pobs) − robs − εenv for each link ℓ. Here, Jee denotes the end-effector Jacobian; dself and denv,ℓ are the minimum distances to self-collision and to the ℓ-th robot link’s collision with the obstacle, respectively, as predicted by a deep neural network; and ε· > 0 denote safety margins.

The optimization is solved via QP relaxation of the barrier inequalities via Jacobian linearization. p. 2
Where the paper says it

Here, Jee denotes the end-effector Jacobian; dself and denv,ℓ are the minimum distances to self-collision and to the ℓ-th robot link’s collision with the obstacle, respectively, as predicted by a deep neural network; and ε· > 0 denote safety margins. The optimization is solved via QP relaxation of the barrier inequalities via Jacobian linearization.

The Gauss–Newton Hessian approximation enables real-time at 100 Hz. p. 2
Where the paper says it

The optimization is solved via QP relaxation of the barrier inequalities via Jacobian linearization. The Gauss–Newton Hessian approximation enables real-time at 100 Hz.

However, the method relies on a perfectly accurate perception. p. 2
Where the paper says it

The Gauss–Newton Hessian approximation enables real-time at 100 Hz. However, the method relies on a perfectly accurate perception.

GUARD addresses this limitation via an uncertainty-aware ICP. p. 2
Where the paper says it

However, the method relies on a perfectly accurate perception. GUARD addresses this limitation via an uncertainty-aware ICP.

--- Page 4 ---

Fig. 5: 7-DoF manipulator follows a 3D lemniscate with a dynamic obstacle; (a) setup; (b) minimum robot–obstacle distance for RMPCC and GUARD (blue) and red; dashed: safety margin εobs; green boxes indicate collisions. p. 3

Where the paper says it

distance Fig. 5: 7-DoF manipulator follows a 3D lemniscate with a dynamic obstacle; (a) setup; (b) minimum robot–obstacle distance for RMPCC (blue) and GUARD (red); dashed: safety margin εobs; green boxes indicate collisions.

p. 3
Where the paper says it

distance Fig. 5: 7-DoF manipulator follows a 3D lemniscate with a dynamic obstacle; (a) setup; (b) minimum robot–obstacle distance for RMPCC (blue) and GUARD (red); dashed: safety margin εobs; green boxes indicate collisions.

--- Page 5 ---

Fig. 5: 7-DoF manipulator follows a 3D lemniscate with a dynamic obstacle; (a) setup; (b) minimum robot–obstacle distance for RMPCC (blue) and GUARD (red); dashed: safety margin εobs; green boxes indicate collisions. p. 3

Where the paper says it

distance Fig. 5: 7-DoF manipulator follows a 3D lemniscate with a dynamic obstacle; (a) setup; (b) minimum robot–obstacle distance for RMPCC (blue) and GUARD (red); dashed: safety margin εobs; green boxes indicate collisions.

--- Page 5 ---

Fig. 5: 7-DoF manipulator follows a 3D lemniscate with a dynamic obstacle; (a) setup; (b) minimum robot–obstacle distance for RMPCC and GUARD (blue) and red; dashed: safety margin εobs; green boxes indicate collisions.

Green — the paper says it, and the page is printed. Red — no passage carries it, so treat that sentence as unverified. The same check runs on your own text: check a summary against its source, $5.

Improvements for AI systems

  1. Active PKO via Concept Feedback allows GUARD to adapt kernel parameters online by matching inlier distributions with empirical residuals, specifically adapting the robust kernel parameters by matching an inlier distribution with the empirical residual as described in Section II.

  2. Uncertainty-aware Robot Control enables the robot controller to modulate safety based on perception uncertainty, where "The scalar risk and per-concept posteriors modulate (i)the CBF relaxation (large slack penalties at high risk), (ii)collision margins and desired speed vdes, and (iii)soft weights wc,wl,wo,wvs to trade efficiency for conservatism if perception uncertainty spikes."

  3. Risk Mapping and Safety under Parameter Adaptation allows GUARD to derive a bounded risk measure rho k from concept posteriors and entropy uk using the formula rho k = clip[0,1] beta0 uk + X c∈C beta c πk(c), which then linearly inflates margins, increases slack penalty, and reduces speed to tighten the safe set.

  4. The system can flag out-of-distribution frames using a reject rule defined as "OODk = 1 if uk > τu or max c∈C πk(c) < τp i, which triggers freezing kernel updates and reducing v eff des while inflating margins via (9)."

  5. GUARD combines traditional control with learning algorithms to foster the development of safe, yet efficient and flexible applications by unifying reactive model predictive contouring control (RMPCC) with uncertainty-aware ICP.

Abstract

This paper presents the framework GUARD (Guided robot control via Uncertainty attribution and probAbilistic kernel optimization for Risk-aware Decision making) that combines a technique from probabilistic state estimation with an uncertainty identification method to derive critical thresholds for robot control algorithms. The first part focuses on complementing a method for probabilistic kernel optimization (PKO) by a sensitivity-aware uncertainty attribution technique. Next, the estimated uncertainties and their sources are forwarded to the robot controllers to adapt safety margins and trigger the initialization of safe backup trajectories. To validate GUARD's applicability and performance, experiments are conducted on a traditional model predictive control (MPC) algorithm and a reinforcement learning (RL) based controller. The results demonstrate that GUARD reduces collision rates by 44-67% in the RL-based evaluation, while decreasing backup policy activation by 50-75% in the medium- and high-uncertainty profiles. In the MPC simulation, GUARD successfully avoids collisions. By unifying the probabilistic kernel optimization algorithm from robot state estimation with the uncertainty estimation method for learning-based control, GUARD brings together traditional techniques and learning for safe and efficient robot applications.

Sources

Related papers