Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Visual-RRT: Finding Paths toward Visual-Goals via Differentiable Rendering

About

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 demonstration videos where precise goal configurations are unavailable. In this paper, we propose visual-RRT (vRRT), a motion planner that enables visual-goal planning by unifying gradient-based exploitation from differentiable robot rendering with sampling-based exploration from RRTs. We further introduce (i) a frontier-based exploration-exploitation strategy that adaptively prioritizes visually promising search regions, and (ii) inertial gradient tree expansion that inherits optimization states across tree branches for momentum-consistent gradient exploitation. Extensive experiments across various robot manipulators including Franka, UR5e, and Fetch demonstrate that vRRT achieves effective visual-goal planning in both simulated and real-world settings, bridging the gap between sampling-based planning and vision-centric robot applications. Our code is available at https://sgvr.kaist.ac.kr/Visual-RRT.

Sebin Lee, Jumin Lee, Taeyeon Kim, Younju Na, Woobin Im, Sung-Eui Yoon• 2026

Related benchmarks

TaskDatasetResultRank
Visual-goal pose reconstructionFranka Robot Environment
Success Rate100
12
Visual-goal pose reconstructionUR5e Robot Environment
Success Rate100
12
Visual-goal pose reconstructionFetch Robot Environment
Success Rate (%)100
12
Visual-goal motion planningFranka 0.5 rad bin 1.0 (test)
Success Rate (SR)93
4
Visual-goal motion planningFranka rad bin 1.0 (test)
Success Rate89
4
Visual-goal motion planningFranka 1.5 rad bin 1.0 (test)
Success Rate81.7
4
Visual-goal motion planningFranka 2.0 rad bin 1.0 (test)
Success Rate (SR)67.7
4
Visual-goal motion planningFranka 2.5 rad bin 1.0 (test)
Success Rate44.7
4
Visual-goal motion planningFranka Avg. 1.0 (test)
Success Rate (SR)75.2
4
Visual-goal motion planningUR5e 0.5 rad bin 1.0 (test)
Success Rate (SR)87.3
4
Showing 10 of 26 rows

Other info

Follow for update