NVIDIA Isaac Lab
PulseAugur coverage of NVIDIA Isaac Lab — every cluster mentioning NVIDIA Isaac Lab across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
New safety layer for deep reinforcement learning in quadrotors
Researchers have developed CALOS, a Control-Affine Lyapunov On-manifold Safety layer designed to enforce safety constraints in deep reinforcement learning for quadrotor control. This runtime layer formulates attitude an…
-
New RL method enhances autonomous drone landings in rough seas
Researchers have developed a novel reinforcement learning approach called Curriculum-Based Adversarial Heterogeneous Agent Reinforcement Learning (HARL-AC) to improve the autonomous landing of quad-copter drones in chal…
-
NVIDIA powers AI robotics and robotaxis with advanced physical AI platforms
NVIDIA is collaborating with Skild AI to advance robotics by enabling robots to learn new tasks from single video demonstrations, a technique known as in-context learning. This approach, powered by NVIDIA's AI infrastru…
-
Prosthetic hand data to train industrial robots
PSYONIC, a maker of prosthetic hands, is collaborating with NVIDIA and ABB Robotics to address the data problem in physical AI. Their approach involves using data captured from their touch-sensing Ability Hand, worn by …
-
Dual-critic architecture boosts humanoid robot loco-manipulation
Researchers have found that the architecture of critics in reinforcement learning significantly impacts humanoid robot performance. A dual-critic system, which uses separate critics for locomotion and manipulation, outp…
-
AWS SageMaker integrates NVIDIA Isaac Lab for robot RL training
Amazon SageMaker AI is enhancing robot reinforcement learning by integrating NVIDIA Isaac Lab. This allows for accelerated training of robot policies, such as for the Unitree H1 humanoid, using either SageMaker HyperPod…
-
NVIDIA Research advances robotics with sim-to-real breakthroughs
NVIDIA Research presented eight new papers at the International Conference on Robotics and Automation (ICRA) detailing advancements in simulation-to-real transfer for robotics. These papers showcase methods for robots t…
-
DIY Star Wars BDX droid learns to walk via reinforcement learning
An individual has recreated a Star Wars droid, known as the BDX, using a custom build that incorporates reinforcement learning for its movement. The project significantly reduced costs by using QDD motors and a repurpos…
-
Robots navigate using AI-powered depth estimation, ditching LiDAR
Researchers have developed a novel teacher-student framework for robot navigation that replaces traditional LiDAR sensors with vision-based monocular depth estimation. A teacher policy, trained with privileged LiDAR dat…