用好奇心引导扩散模型，提升机器人行为可靠性。
Curiosity-Diffuser: Curiosity Guide Diffusion Models for Reliability
- 用RND模块评估行为与训练数据的偏离度，指导生成更可信轨迹。
- 在仿真和真实场景中，生成动作与训练数据相似度提升37%以上。
- 适合关注机器人安全与泛化能力的研究者使用。
神经网络模型在机器人智能中的不稳定性是关键瓶颈，导致模仿策略可能产生幻觉行为，影响实际应用安全性。本文提出Curiosity-Diffuser，通过随机网络蒸馏（RND）模块评估模型行为与训练数据的偏离程度，并利用分类器引导扩散模型最小化好奇心，减少推理时的过度泛化。同时，设计了一种计算高效的可靠性评估指标，量化生成行为与训练数据的相似性，促进可靠性学习研究。仿真与真实世界实验验证了该方法在多种场景下的有效性，显著提升任务表现，生成动作与训练数据的相似度提高37%以上。代码已开源。
原文摘要 · Abstract (English)
One of the bottlenecks in robotic intelligence is the instability of neural network models. This leads to risks when applying intelligence in the physical world. Specifically, imitation policy based on neural network may generate hallucinations, leading to inaccurate behaviors that impact the safety of real-world applications. To address this issue, this paper proposes the Curiosity-Diffuser, aimed at guiding the conditional diffusion model to generate trajectories with lower curiosity, thereby improving the reliability of policy. The core idea is to use a Random Network Distillation (RND) curiosity module to assess whether the model's behavior aligns with the training data, and then minimize curiosity by classifier guidance diffusion to reduce overgeneralization during inference. Additionally, we propose a computationally efficient metric for evaluating the reliability of the policy, measuring the similarity between the generated behaviors and the training dataset, to facilitate research about reliability learning. Finally, simulations and real-world experiments verify the effectiveness and applicability of the proposed method to a variety of scenarios, showing that Curiosity-Diffuser significantly improves task performance and produces behaviors that are more similar to the training data. The code for this work is available at: github.com/CarlDegio/Curiosity-Diffuser
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。