发表机构
DGIST; KAIST（韩国科学技术院大邱庆北校区; 韩国科学技术院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究社交机器人在拥挤环境中统一预测与规划问题，提出基于模型合并的不相交参数训练框架DPT，通过分布式参数学习减轻技能冲突，稀疏合并提升性能，在标准基准测试中验证其在机器人导航上通用且有效。
AI 中文摘要
准确预测周围智能体的运动和安全运动规划是社交机器人在拥挤环境中导航的两个紧密耦合的关键任务。在资源受限的边缘设备上部署这些系统需要紧凑、统一的模型来同时执行这两项任务。然而，在这些紧凑的共享编码器中，最近的统一模型常常忽略了预测邻居行为与以自我为中心的安全规划这两个不同目标所产生的严重表示冲突。为解决此问题，我们首先识别出技能冲突现象，即重叠参数分配导致不同任务争夺相同权重，使模型无法充分专注于个体技能。为解决这一问题，我们提出了一种基于模型合并的新框架——不相交参数训练（DPT）。DPT通过分布式参数学习减轻技能冲突导致的性能下降，在合并前分离每个任务的关键参数区域并保留其核心能力。此外，我们发现稀疏合并（仅选择性地整合每个任务最具影响力的参数而非组合所有特定任务参数）通过防止相邻特征间的干扰并集中表示能力产生最优性能。DPT可与多种合并方法并行应用。在标准人群导航基准测试（JRDB和JTA）上的评估表明，我们的框架具有卓越性能，验证了其在安全、资源高效机器人导航方面的通用性和有效性。
英文摘要
Accurate motion prediction of surrounding agents and safe motion planning are two closely coupled key tasks for social robot navigation in crowded environments. Deploying these systems on resource-constrained edge devices necessitates compact, unified models that can perform both tasks simultaneously. However, within these compact shared encoders, recent unified models often overlook severe representational conflicts that arise from the distinct objectives of predicting neighbor behaviors versus ego-centric safety planning. To address this issue, we first identify the Skill Conflict$\unicode{x2014}$a phenomenon where overlapping parameter assignments cause distinct tasks to compete for the same weights, preventing the model from fully specializing in individual skills. To resolve this, we propose a novel model-merging-based framework, Disjoint Parameter Training (DPT). DPT mitigates performance degradation caused by Skill Conflict through distributed parameter learning, which separates the key parameter regions of each task while preserving their core capabilities prior to merging. In addition, we observe that sparse merging, which selectively integrates only the most influential parameters for each task rather than combining all task-specific parameters, yields optimal performance by preventing interference among adjacent features and concentrating representational capacity. DPT can be applied in parallel with a variety of merging methods. Evaluated on standard crowd navigation benchmarks (JRDB and JTA), our framework demonstrates superior performance, validating its versatility and effectiveness for safe, resource-efficient robot navigation.
CommentsAccepted at ECCV 2026. 38 pages, 14 figures. Project page: https://dpt2026.github.io/
