毫末联合清华AIR等发布全新自动驾驶规划算法Diffusion Planner 1月28日，毫末智行联合清华大学AIR智能产业研究院、自动化所、港中文、上海交大、上海人工智能实验室在ICLR 2025上正式发布了最新自动驾驶研究成果《Diffusion-based Planning for Autonomous Driving with Flexible Guidance》。该算法创新性地设计了一种基于Diffus...
1月28日,毫末智行联合清华大学AIR智能产业研究院、自动化所、港中文、上海交大、上海人工智能实验室在ICLR 2025上正式发布了最新自动驾驶研究成果《Diffusion-based Planning for Autonomous Driving with Flexible Guidance》。该算法创新性地设计了一种基于Diffusion Transformer 的自动驾驶规划模型架构——Diffusion Planner,...
Q. Chen, and Z. Song, "Diffusion based path planning in mobile actuator-sensor networks (MAS-net) - some preliminary results," in Proc. of SPIE Conf. on Intelligent Computing: Theory and Applications II, part of SPIE's Defense and Security, (Orlando, FL, USA), Ap...
.com/watch?v=G3u5R4zYLNs DiPPeST: Diffusion-based Path Planner for Synthesizing Trajectories Applied on Quadruped Robots Maria Stamatopoulou, Jianwei Liu, Dimitrios Kanoulas We present DiPPeST, a novel image and goal conditioned diffusion-based trajectory generator for quadrupedal robot path planning...
Iterative Diffusion-Based Refinement 场景流估计,是计算机视觉领域的一项基础任务,旨在预测动态场景的每个点的三维位移。然而,前期的工作通常由于局部限制的搜索范围导致相关性不可靠,并且由于粗到细结构而产生累积误差。 为缓解这些问题,提出一种新的基于扩散概率模型的场景流估计网络(DifFlow3D)来推断不确定性。设计迭代...
1、机器人规划/智能决策 SkillDiffuser: Interpretable Hierarchical Planning via Skill Abstractions in Diffusion-Based Task Execution 扩散模型已展示在机器人轨迹规划方面的潜力。然而,从高级指令生成连贯的轨迹仍具有挑战性,特别是对于需要多个序列技能的长距离组合任务。
Adaptive diffusion smoothing: A diffusion‐based method to reduce IMRT field complexityTherapeutic applications, including brachytherapyTreatment planningQuality assurance in radiotherapyDosimetry/exposure assessmentdiffusiondosimetryphantomsquality assuranceradiation therapy...
核心概念 扩散模型，如Diffuser，通过迭代的去噪过程产生数据，逆过程则用于建模复杂分布。这些模型在决策轨迹的建模中展现出了强大威力，特别是在离线RL环境中，它们能够处理模型-free和model-based策略的融合。方法论 Diffuser以模仿学习（通过模仿专家策略）和强化学习（扩散模型与RL的集成）为两大支柱。轨迹...
110 (2024-01-7) Freetalker Controllable Speech and Text-Driven Gesture Generation Based on Diffusion Models for Enhanced Speaker Naturalness https://arxiv.org/pdf/2401.03476.pdf 111 (2023-10-13) Generative Skill Chaining Long-Horizon Skill Planning with Diffusion Models ...
011 (2024-06-4) Learning Image Priors through Patch-based Diffusion Models for Solving Inverse Problems https://arxiv.org/pdf/2406.02462.pdf 012 (2024-06-4) Finding NeMo Localizing Neurons Responsible For Memorization in Diffusion Models