HUST, PKU and Keenon Robotics unveil AdaRoboVLG for context-aware robot grasping
jiqizhixin · x · 2026-10-03
Researchers from Huazhong University of Science and Technology, Peking University, and Keenon Robotics present AdaRoboVLG, tackling Vision-Language-Grasping (VLG): robots must decide how to grasp based on natural language and context—grab a cup by the handle to pour, leave the handle free when handing it over, and update grasp points as objects move on conveyor belts.
Most existing VLG methods are end-to-end and struggle to handle four challenges at once:
- Spatial: locating targets and avoiding collisions amid clutter and occlusion
- Cognitive: understanding object affordances
- Temporal: tracking dynamically changing states
- Embodiment: adapting to different gripper mechanics
More from Embodied
- Neuralink pretrained AI on 50,000 hours of brain activity, hits 11.32 bps cursor-control record — mark_k · 2026-10-04
- Training a 128k-param neural cellular automata to 'see around corners' with sound — yacineMTB · 2026-10-04
- CoreWeave's Physical AI Lead Explains Why Robots Hit the Sim-to-Real Gap — thursdai_pod · 2026-10-04
- Replacing CAD with code: LLM-written build123d Python scripts design entire robots — natesiggard · 2026-10-03
- Sharpa D01 humanoid robot outperforms humans at grasping soft dropped objects — CyberRobooo · 2026-10-03
- The $899 Mac Mini M6 was built for 24/7 agentic computing — most owners use it to check email — hey_abusiddik · 2026-10-03