NVIDIA's Three Neural Breakthroughs Transform Robot Learning at CoRL 2025
Source: developer.nvidia.com · May 26, 2026
Summary
NVIDIA Research introduced NeRD, Dexplore, and VT-Refine at CoRL 2025, enhancing simulation with learned dynamics, enabling efficient exploration, and combining vision-tactile sensing for bimanual assembly. These innovations represent a first-of-its-kind capability in integrating multiple neural approaches for practical robot learning.
Related research
All papers →Recent papers matching 4 keywords from this headline
Parallel Differentiable Reachability for Learning and Planning with Certified Neural Dynamics and Controllers
Keyi Shen, Glen Chou
2026
A deep reinforcement learning and a dynamic graph neural network-based scheduling agent to control a multi-task robot
Hedi Boukamcha, Anas Neumann, Monia Rekik +3 more
Robotics and Computer-Integrated Manufacturing · 2026
RobKiNet: Robotic Kinematics Informed Neural Network for optimal robot configuration prediction
Yanlong Peng, Zhigang Wang, Yisheng Zhang +5 more
Robotics and Autonomous Systems · 2026
Integrated Adaptive MIMO Higher Order Sliding Mode Controller and Neural Network-Based Disturbance Estimation: Application to a Heavy-Lift COUAV
Parvin Mahmoudabadi, Karl D. von Ellenrieder, Matthias Moroder +1 more
Robotics and Autonomous Systems · 2026