$BOT robot

Latest papers

1. RAPID: Robot Agentic Programming from Demonstrations cs.RO · 24 Sep · 5 hits

   …have demonstrated enormous success in solving complex programming problems. To leverage their potential for robot systems, this work introduces Robot Agentic Programming from Demonstrations (RAPID), which…

2. ReVAMP: Vector-Accelerated Motion Planning for Kinematically-Constrained Systems via Reparameterization cs.RO · 24 Sep · 1 hit

   Robots often must satisfy one or more constraints during motion planning for real-world tasks. When such…

3. Training-free Behavior Cloning cs.RO · 24 Sep · 1 hit

   …that best reconstructs the recent runtime observation--action history. Across simulated benchmarks and real-robot deployments, BPC is competitive with learned policies such as $\pi_{0.5}$ (surpassing it in some…

4. Faster Visuomotor Policy Learning on Action Manifolds via Riemannian MeanFlow cs.RO · 24 Sep · 4 hits

   Visuomotor policies learn a direct map from raw sensory observations to robot action sequences. Policies based on Diffusion and Flow Matching capture the multimodal distribution…

5. Self-Adaptive VLA for Robust Robot Deployment cs.RO · 24 Sep · 2 hits

   …workstations compared to the base policy. Our approach provides a pathway for robust large-scale real-world robot deployments and easier maintenance. See videos at https://icefoxzhx.github.io/self-adaptive-vla.

6. M3GD: Multi-Modal Multi-View Geometric Diffusion for Camera--LiDAR Novel View Synthesis cs.RO · 24 Sep · 1 hit

   …LiDAR acts as a geometric query linking the requested view to source observations. Deployment on a ground robot demonstrates practical real-world operation, with a configurable quality--cost trade-off controlled by…

7. Body-Grounded Replanning for Physically Adaptive Manipulation cs.RO · 24 Sep · 2 hits

   Manipulation requires not only reasoning about the external environment, but also about the robot's physical condition. A strategy may remain geometrically feasible while becoming physically unsuitable…

8. Res-HIL: Human-Guided Residual Reinforcement Learning for Sample-Efficient Dexterous Manipulation cs.RO · 24 Sep · 1 hit

   Imitation learning enables robots to acquire manipulation skills from demonstrations, but the resulting policies can fail outside the…