用动态优先级解决多目标冲突，让机器人在复杂环境中自主导航与推物。
Riding the Shifting Potential: When Reactive Control Suffices for Multi-Goal Behavior
- 基于图模型动态调整目标优先级，实时投影低优先级梯度消除冲突
- 在非凸障碍物间导航成功率达100%，远超基线方法的0%和55%
- 无需示教或重训练，可直接部署到真实机器人上
反应式控制常被认为无法应对多目标任务，因目标冲突会引发局部极小。我们提出该限制并非本质，而是源于静态编码无法反映目标间的动态交互。本文利用图结构世界模型中的交互关系，引入零空间投影机制：通过连续根据当前状态确定优先级，将低优先级梯度投影到高优先级梯度的零空间中，实现冲突就地化解。我们在两个关键场景中验证：非凸障碍物环绕导航（静态势场方法根本失效）和非凸物体平面推移。所提方法在一百种配置下均达100%成功率，而最陡下降基线为0%，扩散策略约55%。该框架可直接迁移至真实机器人，通过相同机制适应感知与运动学约束。
原文摘要 · Abstract (English)
Reactive control is often considered insufficient for multi-objective tasks because conflicting objectives give rise to local minima. We argue this limitation is not inherent but arises from static encodings that fail to reflect how objectives currently interact. We exploit the interaction structure encoded in a graph-based world model by extending it with nullspace projections: conflicts are resolved where they arise by projecting lower-priority gradients into the nullspace of higher-priority ones, with priorities determined continuously from the current state. We demonstrate this in two domains where conflicts between objectives are central: navigation around non-convex obstacles, where static potential fields fundamentally fail, and planar pushing of non-convex objects, where our method achieves $100\%$ success across one-hundred configurations versus $0\%$ for the steepest-descent baseline and ${\sim}55\%$ for diffusion policy, without demonstrations or retraining. The same formulation transfers directly to a real robot with additional perceptual and kinematic constraints, accommodating them through the same mechanism.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。