A distilled student policy using monocular depth estimation from cameras outperforms a 2D LiDAR teacher policy in navigating complex 3D obstacles while running fully onboard a Jetson Orin.
Domain randomization for transferring deep neural networks from simulation to the real world
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.RO 3representative citing papers
A unified meta-representation learned from past observations combined with state-feedback calibration enables general disturbance estimation with proven convergence.
A GNN-augmented SAC policy that encodes tensegrity topology as a graph improves sample efficiency and enables zero-shot sim-to-real locomotion on a 3-bar tensegrity robot.
citing papers explorer
-
Learning Vision-Based Omnidirectional Navigation: A Teacher-Student Approach Using Monocular Depth Estimation
A distilled student policy using monocular depth estimation from cameras outperforms a 2D LiDAR teacher policy in navigating complex 3D obstacles while running fully onboard a Jetson Orin.
-
Unified Meta-Representation and Feedback Calibration for General Disturbance Estimation
A unified meta-representation learned from past observations combined with state-feedback calibration enables general disturbance estimation with proven convergence.
-
Morphology-Aware Graph Reinforcement Learning for Tensegrity Robot Locomotion
A GNN-augmented SAC policy that encodes tensegrity topology as a graph improves sample efficiency and enables zero-shot sim-to-real locomotion on a 3-bar tensegrity robot.