PointPilot: Unified Robotic Manipulation via Object-Centric 3D Point Flow Prediction
cs.RO
Submitted: 2026-11-02
Updated: 2026-11-02
Project page: https://homangab.github.io/track2act
Terminology
Sources
- SAM 3: Segment Anything with Concepts
- MolmoPoint: Better Pointing for VLMs with Grounding Tokens
- Manipulate-Anything: Automating Real-World Robots using Vision-Language Models
- CoPa: General Robotic Manipulation through Spatial Constraints of Parts with Foundation Models
- ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation
- CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation
- PETR: Position Embedding Transformation for Multi-View 3D Object Detection
- PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images
- ImaginationPolicy: Towards Generalizable, Precise and Reliable End-to-End Policy for Robotic Manipulation
- Open X-Embodiment: Robotic Learning Datasets and RT-X Models
- OmniManip: Towards General Robotic Manipulation via Object-Centric Interaction Primitives as Spatial Constraints
- SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
- Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models
- 4D-VLA: Spatiotemporal Vision-Language-Action Pretraining with Cross-Scene Calibration
- MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction
- X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model
- TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies
- 3DFlowAction: Learning Cross-Embodiment Manipulation from 3D Flow World Model
- Dexterity-BEV: Aligning 3D World and Actions for Generalizable Robot Policies Learning
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation