UC Berkeley — Berkeley AI Research (BAIR) & Robotics
Global leader in robot learning and reinforcement learning for robotics. Berkeley's DexNet grasp planning system and deep RL for manipulation have transformed how robots learn from data.
Notable achievements
DexNet grasp planning, Dactyl predecessor research, robot learning from demonstrations, Brett the robot, RT-2 collaboration with Google.
Notable work
Recent publications
All papers →Matched by this lab's specialties (keyword overlap + direct affiliation)
PAEAR: Point Clouds Area Exploration and Active Recognition method driven by reinforcement learning for robotic welding
Yong Tao, Donghua Tan, Fan Ren +6 more
Robotics and Computer-Integrated Manufacturing · 2026
Multi-pass cutting parameters optimisation with causal reinforcement learning for deformation control of thin-walled parts
Fengyi Lu, Guanghui Zhou, Chao Zhang +2 more
Robotics and Computer-Integrated Manufacturing · 2026
Multi-parameter convolutional coordinated planning for high precision robotic grinding of complex surfaces
Haoyuan Zhou, Huan Zhao, Guanbo Fei +3 more
Robotics and Computer-Integrated Manufacturing · 2026
A hierarchical approach to imitation learning for manipulation tasks requiring time varying forces
Rishabh Shukla, Adithya Santhosh, Shaili Gandhi +2 more
Robotics and Computer-Integrated Manufacturing · 2026
MA2MB: Multi-agent mutual-advising model-based reinforcement learning for pursuit and evasion games
Baolin Zhao, Qi Guo, Xiandong Wang +2 more
Robotics and Autonomous Systems · 2026
Container Unloading via Reinforcement Learning: Picking Order, Deadlock Avoidance, and Proof-of-Concept Simulation
Jan Rüdiger, Max Schenke, Daniel Weber
2026