用不确定性自适应调整重规划频率，提升动态避障效率。
Dynamic Obstacle Avoidance through Uncertainty-Based Adaptive Planning with Diffusion
- 根据动作预测不确定性动态调节重规划频率
- 长程规划下轨迹长度提升13.5%，奖励提高12.7%
- 适合需要高效避障的机器人路径规划场景
将强化学习视为序列建模问题，近期工作实现了使用生成模型（如扩散模型）进行规划。尽管这些模型在确定性环境中能有效预测长时程状态轨迹，但在存在移动障碍物的动态环境中面临挑战。有效的碰撞避免需要持续监测与自适应决策。虽然每步重规划可保证安全，但会因重复预测重叠状态序列而引入巨大计算开销——尤其对依赖迭代采样的扩散模型而言代价高昂。本文提出一种自适应生成式规划方法，根据动作预测的不确定性动态调整重规划频率。该方法在减少频繁、高成本且冗余重规划的同时，维持了鲁棒的避障性能。实验表明，在长时程规划中，平均轨迹长度提升13.5%，平均奖励增加12.7%，表明碰撞率降低，环境导航能力增强。
原文摘要 · Abstract (English)
By framing reinforcement learning as a sequence modeling problem, recent work has enabled the use of generative models, such as diffusion models, for planning. While these models are effective in predicting long-horizon state trajectories in deterministic environments, they face challenges in dynamic settings with moving obstacles. Effective collision avoidance demands continuous monitoring and adaptive decision-making. While replanning at every timestep could ensure safety, it introduces substantial computational overhead due to the repetitive prediction of overlapping state sequences -- a process that is particularly costly with diffusion models, known for their intensive iterative sampling procedure. We propose an adaptive generative planning approach that dynamically adjusts replanning frequency based on the uncertainty of action predictions. Our method minimizes the need for frequent, computationally expensive, and redundant replanning while maintaining robust collision avoidance performance. In experiments, we obtain a 13.5% increase in the mean trajectory length and a 12.7% increase in mean reward over long-horizon planning, indicating a reduction in collision rates and an improved ability to navigate the environment safely.
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。