Visual-RRT：通过可微渲染寻找通向视觉目标的路径
Visual-RRT: Finding Paths toward Visual-Goals via Differentiable Rendering
把可微机器人渲染当作视觉目标的对齐信号，与 RRT 的采样探索结合，为视觉目标条件下的操作规划提供了可复用的「梯度利用 + 采样探索」框架；做视觉目标设定、视觉伺服或渲染驱动优化的研究者可直接借用其前沿式探索-利用调度与惯性梯度树扩展。
原文依据 unifying gradient-based exploitation from differentiable robot rendering with sampling-based exploration from RRTs
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论快速扩展随机树（RRT）因其鲁棒性与理论保证而被广泛用于机器人运动规划。然而，现有基于 RRT 的规划器要求以数值关节角形式显式给定目标构型，而许多实际应用通过图像或示范视频等视觉观测来提供目标设定，此时精确的目标构型并不可得。本文提出 visual-RRT（vRRT），一种通过统一来自可微机器人渲染的梯度利用与来自 RRT 的采样探索来实现视觉目标规划的運動规划器。我们进一步引入（1）一种基于前沿的探索-利用策略，自适应地优先搜索视觉上更有希望的区域；（2）惯性梯度树扩展，在树的分支之间继承优化状态，以实现动量一致的梯度利用。在包括 Franka、UR5e 与 Fetch 在内的多种机器人机械臂上的大量实验表明，vRRT 在仿真与真实环境中均能实现有效的视觉目标规划，弥合了基于采样的规划与以视觉为中心的机器人应用之间的差距。代码见 https://sgvr.kaist.ac.kr/Visual-RRT。
英文原文摘要 1273 字符
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 (1) a frontier-based exploration-exploitation strategy that adaptively prioritizes visually promising search regions, and (2) 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.