结合人类干预的图重加权行为克隆用于精确机器人操纵
Graph-Reweighted Behavior Cloning with Human Interventions for Precise Robotic Manipulation
AI总结：
本文提出 GR-BC 框架，通过构建目标可达性图对动作块加权，复用失败轨迹片段，在四项精确操纵任务上使 VLA 模型经少量离线迭代后达 91% 成功率，无需额外训练。
摘要：
长程精确操纵会为后训练的视觉-语言-动作（VLA）模型生成混合质量的数据：即使是成功的演示和人类干预辅助的 rollout（ rollout 指策略执行轨迹）也可能包含迂回、犹豫、失败尝试和不完善的恢复过程。核心挑战在于识别哪些动作块真正推进任务，而非统一克隆或丢弃不完善轨迹。我们提出图重加权行为克隆（GR-BC），这是一种离线迭代后训练框架，它在演示和迭代收集的 rollout（包括带人类干预的成功与失败回合）上构建任务条件的目标可达性图。反向图搜索计算数据集支持内任务成功的最小剩余步骤，每个动作块的权重由其执行减少该潜力的程度决定。这种基于结果的权重复用失败轨迹中可恢复片段，将人类干预作为恢复路径，甚至在成功轨迹内部对局部退化动作块进行降权。新的 rollout 通过追加到图中并重新运行搜索来纳入，无需训练奖励模型、动作条件评论者或进度预测器。在四项精确操纵任务和三种 VLA 主干网络上，GR-BC 提升了单轮监督微调效果，在几次离线迭代后达到 91% 的成功率，无需轨迹比较或进度标签。更多细节和视频可访问：this https URL
英文摘要：
Long-horizon precise manipulation produces mixed-quality data for post-training vision-language-action (VLA) models: even successful demonstrations and intervention-assisted rollouts may contain detours, hesitations, failed attempts, and imperfect recoveries. The key challenge is to identify which action chunks actually advance the task, rather than uniformly cloning or discarding imperfect trajectories. We propose Graph-Reweighted Behavior Cloning (GR-BC), an offline iterative post-training framework that builds a task-conditioned goal-reachability graph over demonstrations and iteratively collected rollouts, including both successful and failed episodes with human interventions. Reverse graph search computes minimal remaining steps to task success within the dataset support, and each action chunk is weighted by how much its execution reduces this potential. This consequence-based weighting reuses recoverable segments from failed trajectories, leverages interventions as recovery paths, and down-weights locally regressive chunks even inside successful trajectories. New rollouts are incorporated by appending them to the graph and rerunning search, without training a reward model, action-conditioned critic, or progress predictor. Across four precise manipulation tasks and three VLA backbones, GR-BC improves single-round supervised fine-tuning and reaches 91% success after a few offline iterations, without trajectory comparisons or progress labels. More details and videos are available at: https://gr-bc.github.io
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。
