AI RESEARCH
Visual-RRT: Finding Paths toward Visual-Goals via Differentiable Rendering
arXiv CS.CV
•
ArXi:2604.16388v1 Announce Type: cross Rapidly-exploring random trees (RRTs) have been widely adopted for robot motion planning due to their robustness and theoretical guarantees. However, existing RRT-based planners require explicit goal configurations specified as numerical joint angles, while many practical applications provide goal specifications through visual observations such as images or nstration videos where precise goal configurations are unavailable.