CMP: Robust Whole-Body Tracking for Loco-Manipulation via Competence Manifold Projection
cs.RO, cs.AI, cs.LG
Submitted: 2026-04-08
Updated: 2026-10-12
Comments: Accepted to CoRL 2026 (Spotlight). Project webpage: https://shepherd1226.github.io/CMP
Project page: https://shepherd1226.github.io/CMP
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Safe Exploration in Continuous Action Spaces
- Real-Time Out-of-Distribution Failure Prevention via Multi-Modal Reasoning
- Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer
- Learning Humanoid Standing-up Control across Diverse Postures
- Planning with Diffusion for Flexible Behavior Synthesis
- ManiCM: Real-time 3D Diffusion Policy via Consistency Model for Robotic Manipulation
- SafeFall: Learning Protective Control for Humanoid Robots
- How to Train Your Latent Control Barrier Function: Smooth Safety Filtering Under Hard-to-Model Constraints
- Generalizing Safety Beyond Collision-Avoidance via Latent-Space Reachability Analysis
- Inference-Time Enhancement of Generative Robot Policies via Predictive World Modeling
- Benchmarking Batch Deep Reinforcement Learning Algorithms
- Failure Prediction at Runtime for Generative Robot Policies
- Proximal Policy Optimization Algorithms
- Latent Policy Barrier: Learning Robust Visuomotor Policies by Staying In-Distribution
- Reward Constrained Policy Optimization
- End-to-End Humanoid Robot Safe and Comfortable Locomotion Policy
- CL-DiffPhyCon: Closed-loop Diffusion Control of Complex Physical Systems
- Towards Robust and Secure Embodied AI: A Survey on Vulnerabilities and Attacks
- SHIELD: Safety on Humanoids via CBFs In Expectation on Learned Dynamics
- Safe Learning for Contact-Rich Robot Tasks: A Survey from Classical Learning-Based Methods to Safe Foundation Models
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies