一种用于感知任务规划的全可微神经-软符号框架

中文摘要 AI 辅助

感知规划任务需要两种关键能力：准确感知不确定场景以及遵循逻辑规则规划有效的动作序列。传统方法将感知转换为离散符号事实，然后进行规划，这丢弃了感知不确定性并切断了任务级反馈对感知的影响。我们提出了一种通用的、全可微的神经-软符号框架，在单一计算图中连接视觉感知和任务规划。该框架维护连续的软符号状态，将领域规则提升为可微的软$T_P$转移算子，并在短规划范围内优化动作逻辑值。规划目标的梯度也可以更新感知参数，从而在规划过程中细化与任务相关的感知表示。在Blocksworld上，我们的方法解决了40/40个LatPlan-40任务和596/600个PlanBench-600任务，而LatPlan为33/40，推理模型基线为587/600，同时所需计算量和时间大幅减少。在感知不确定性消融实验中，我们的方法将成功率从感知冻结时的59%提高到83%。我们还在Blocksworld场景中进行了任务与运动仿真，为解码任务计划与下游机器人运动执行之间的兼容性提供了执行级验证。

英文摘要

Perceptual planning tasks require two key capabilities: accurately perceiving uncertain scenes and planning valid action sequences following logical rules. Conventional methods convert perception into discrete symbolic facts and then plan, discarding perceptual uncertainty and severing task-level feedback to perception. We introduce a generic, fully differentiable neuro-soft-symbolic framework that connects visual perception and task planning within a single computational graph. The framework maintains a continuous soft symbolic state, lifts domain rules into a differentiable soft-$T_P$ transition operator, and optimizes action logits over a short planning horizon. Gradients from the planning objective can also update the perception parameters, allowing task-relevant perceptual representations to be refined during planning. On Blocksworld, our method solves 40/40 LatPlan-40 tasks and 596/600 PlanBench-600 tasks, compared with 33/40 for LatPlan and 587/600 for the reasoning-model baseline, while requiring substantially less computation and time. In the perceptual-uncertainty ablation, our method improves the success rate from 59\% with frozen perception to 83\%. We further conduct task-and-motion simulations on Blocksworld scenes, providing an execution-level validation of the compatibility between decoded task plans and downstream robotic motion execution.

发表机构

• Clemson University（克莱姆森大学）

机构由 AI 辅助整理，请以论文原文为准。