arXiv Robotics research summaries for March 7, 2024.

Today's Research Themes (AI-Generated):

• Multi-residual Task Learning (MRTL) synthesizes deep reinforcement learning with conventional control methods for improved autonomous driving.

• LitSim provides realistic long-term interactive traffic simulations to enhance autonomous driving systems by minimizing artificial collisions.

• Control-Barrier-Aided Teleoperation with Visual-Inertial SLAM ensures safe Micro Aerial Vehicle navigation in complex environments using onboard sensors.

• Task-symmetric robot policies are learned through data augmentation and mirror loss functions to leverage symmetry in robotic task performance.

• Human-to-Humanoid Real-Time Whole-Body Teleoperation is enabled using a reinforcement learning framework and an RGB camera.