发表机构
Magiclab Robotics Technology Co., Ltd.; Southeast University（魔法实验室机器人科技有限公司; 东南大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出条件轨迹峰值（CTP）单遍策略框架，联合预测动作块候选、概率质量和轨迹尺度，实现多模态行为与闭环一致性，并在多个基准和真实实验中取得高效推理与高成功率。
AI 中文摘要
多模态模仿学习要求在相同观测下产生多样化的可执行未来轨迹，并在重新规划周期中保持行为一致性。我们提出条件轨迹峰值（CTP），一种单遍策略框架，可联合预测完整的动作块候选、概率质量和轨迹尺度。分布感知峰值特化（DAPS）利用轨迹级后验责任以及质量和尺度调制的重叠约束来特化轨迹峰值。证据门控轨迹信念传输（ETBT）通过可交换候选集之间的几何对应关系维持跨块一致性，同时允许当前策略证据覆盖历史约束。CTP在Push-T上达到91.40%的覆盖率；在D3IL的Avoiding、Aligning和Sorting-2任务上分别取得100.0%、79.72%和84.44%的成功率。在LIBERO上，CTP平均成功率达到97.25%。在真实世界双臂实验中，CTP在双盘任务中保留了两种放置模式，50次试验全部成功。在瓶子直立和将笔放入支架的任务中，它保持了与$\pi_{0.5}$相当的成功率，同时将策略推理延迟从218.24毫秒降低到75.80毫秒。这些结果表明，单遍轨迹建模可以结合多模态行为、闭环一致性和高效推理。
英文摘要
Multimodal imitation learning requires diverse executable futures under the same observation and consistent behavior across replanning cycles. We present Conditional Trajectory Peaks (CTP), a single-pass policy framework that jointly predicts complete action-chunk candidates, probability masses, and trajectory scales. Distribution-Aware Peak Specialization (DAPS) specializes trajectory peaks using trajectory-level posterior responsibilities and mass- and scale-modulated overlap constraints. Evidence-Gated Trajectory Belief Transport (ETBT) maintains cross-chunk consistency through geometric correspondence between exchangeable candidate sets, while allowing current policy evidence to override historical constraints. CTP achieves a coverage score of 91.40% on Push-T; success rates of 100.0%, 79.72%, and 84.44% on D3IL Avoiding, Aligning, and Sorting-2, respectively. On LIBERO, CTP achieves an average success rate of 97.25%. In real-world dual-arm experiments, CTP preserves both placement modes in a two-plate task, succeeding in all 50 trials. On bottle uprighting and pen placement into a holder, it maintains success rates comparable to $π_{0.5}$ while reducing policy inference latency from 218.24 ms to 75.80 ms. These results demonstrate that single-pass trajectory modeling can combine multimodal behavior, closed-loop consistency, and efficient inference.
Comments8 pages, 6 figures, 5 tables. Project page: https://embodied.magiclab.top/works/ctp/index.html
