Prof. Robot: Differentiable Robot Rendering Without Static and Self-Collisions

STATIC COLLISION SELF COLLISION DR. ROBOT PROF. ROBOT (OURS) DR. ROBOT PROF. ROBOT (OURS) Figure 1. Our method improves upon Dr.Robot [32] by additionally enabling differentiable avoidance of static and self-collisions. By learning and integrating a gradient-consistent pose classifier into a differentiable rendering pipeline, the generated pose trajectories are free from physical collisions. The objective is to penalize high collision probabilities during optimization. On the left, our method can push robotic arms away from intersecting objects. On the right, it can also avoid self-collisions. Images are rendered using Blender with meshes.