论文标题
社会NCE：对社会意识的运动表示的对比度学习
Social NCE: Contrastive Learning of Socially-aware Motion Representations
论文作者
论文摘要
学习具有社会意识的运动表示是多代理问题的最新进展的核心，例如人群中的人类运动预测和机器人导航。尽管有前途的进展，但神经网络学到的现有表示仍在努力概括闭环预测（例如，输出碰撞轨迹）。这个问题主要来自非i.i.d。顺序预测的性质与分布不良的培训数据结合使用。直观地，如果训练数据仅来自安全空间中的人类行为，即来自“积极”的例子，那么学习算法很难捕获诸如碰撞之类的“负”示例的概念。在这项工作中，我们旨在通过自学对负面示例进行显式建模来解决这个问题：（i）我们引入了社会对比损失，通过从合成负面的情况下辨别地面真实事件来使提取的运动表示正常； （ii）我们基于我们对罕见但危险情况的先验知识来构建信息的负面样本。我们的方法大大降低了最近的轨迹预测，行为克隆和增强学习算法的碰撞率，在几种基准上的最先进方法表现优于最先进的方法。我们的代码可在https://github.com/vita-epfl/social-nce上找到。
Learning socially-aware motion representations is at the core of recent advances in multi-agent problems, such as human motion forecasting and robot navigation in crowds. Despite promising progress, existing representations learned with neural networks still struggle to generalize in closed-loop predictions (e.g., output colliding trajectories). This issue largely arises from the non-i.i.d. nature of sequential prediction in conjunction with ill-distributed training data. Intuitively, if the training data only comes from human behaviors in safe spaces, i.e., from "positive" examples, it is difficult for learning algorithms to capture the notion of "negative" examples like collisions. In this work, we aim to address this issue by explicitly modeling negative examples through self-supervision: (i) we introduce a social contrastive loss that regularizes the extracted motion representation by discerning the ground-truth positive events from synthetic negative ones; (ii) we construct informative negative samples based on our prior knowledge of rare but dangerous circumstances. Our method substantially reduces the collision rates of recent trajectory forecasting, behavioral cloning and reinforcement learning algorithms, outperforming state-of-the-art methods on several benchmarks. Our code is available at https://github.com/vita-epfl/social-nce.
