先抓取后规划与失败归因：一种用于精确且可泛化机器人操作的闭环两阶段框架
Grasp-Then-Plan with Failure Attribution: A Closed Two-Stage Framework for Precise and Generalizable Robotic Manipulation
AI总结：
提出GTP-FA框架，通过任务导向的两阶段抓取-规划流程和失败归因模型，在抓取和规划模块中分别注入任务先验和风险惩罚以及针对高风险初始状态进行数据收集和微调，显著提升机器人操作任务的成功率。
摘要：
在机器人操作中，抓取与运动规划之间的紧密耦合常常掩盖失败的真实原因，导致低效的试错过程。为了实现高效的长时域操作，我们提出了GTP-FA（先抓取后规划与失败归因），一种面向任务的两阶段抓取-规划框架，该框架生成抓取候选并根据所选抓取执行下游运动规划。给定失败的操作轨迹，我们学习一个失败归因模型，该模型可泛化到未见过的抓取，并生成失败模式的稳定分布以进行诊断引导的优化。基于这些归因结果，我们以诊断驱动的方式优化两个模块：在抓取侧，我们将任务级先验和风险惩罚注入抓取候选评分和优化中，以抑制不稳定或与任务不兼容的抓取；在规划侧，我们通过数据收集和微调针对高风险初始状态，以解决真正的规划瓶颈。我们在仿真和真实机器人实验中评估了所提出的框架，并表明GTP-FA在基于RL、IL、扩散策略和VLA的设置中提升了相应的基础学习器，实现了显著更高的总体任务成功率。
英文摘要：
In robotic manipulation, the tight coupling between grasping and motion planning often obscures the true source of failure, leading to inefficient trial-and-error. To enable efficient long-horizon manipulation, we propose GTP-FA (Grasp-Then-Plan with Failure Attribution), a task-oriented two-stage grasp-then-plan framework that generates grasp candidates and performs downstream motion planning conditioned on the selected grasp. Given a failed manipulation trajectory, we learn a failure attribution model that generalizes to unseen grasps and produces a stable distribution over failure modes for diagnosis-guided optimization. Based on these attribution results, we then optimize both modules in a diagnosis-driven manner: on the grasping side, we inject task-level priors and risk penalties into grasp candidate scoring and optimization to suppress unstable or task-incompatible grasps; on the planning side, we target high-risk initial states through data collection and fine-tuning to address genuine planning bottlenecks. We evaluate the proposed framework in both simulation and real-robot experiments, and show that GTP-FA improves the corresponding base learners across RL, IL, diffusion-policy, and VLA-based settings, achieving substantially higher overall task success rates.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
