arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.00563cs.ROcs.AIcs.CVcs.LGcs.MA
收藏

用于联合多智能体运动预测的潜在变量序列集Transformers

Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Prediction

Polytechnique Montréal(蒙特利尔综合理工大学);Mila, Quebec AI Institute(米拉-魁北克人工智能研究所);ElementAI / Service Now(元素人工智能/Service Now公司);Algolux(阿尔戈勒克斯公司);McGill University(麦吉尔大学);École de technologie supérieure(高等技术学院);Princeton University(普林斯顿大学)

Roger Girgis, Florian Golemo, Felipe Codevilla, Martin Weiss, Jim Aldon D'Souza, Samira Ebrahimi Kahou, Felix Heide, Christopher Pal

摘要:

鲁棒的多智能体轨迹预测对于机器人系统的安全控制至关重要。一个主要的挑战是有效地学习一个表示,近似的上下文,社会和时间信息的真实联合分布,使规划。我们提出潜在变量序列集Transformers,这是编码器-解码器架构,产生场景一致的多智能体轨迹。我们将这些架构称为“汽车人”。编码器是一个堆栈的交错时间和社会多头自我注意(MHSA)模块交替执行跨时间和社会维度的等变处理。解码器采用可学习的种子参数与时间和社会MHSA模块相结合,使其能够在单个前向传递中有效地对整个未来场景进行推理。AutoBots可以生成一个自我智能体的轨迹,也可以生成场景中所有智能体未来轨迹的分布。对于单智能体预测的情况下,我们的模型在全球nuScenes车辆运动预测排行榜上取得了最佳结果,并在Argoverse车辆预测挑战中取得了很好的结果。在多智能体环境中,我们对TrajNet++数据集的合成分区进行评估,以展示模型的社会一致性预测。我们还展示了我们的模型的一般序列集,并提供说明性的实验建模的顺序结构的多个笔画,使符号的Omniglot数据。AutoBots的一个显着特点是,所有模型都可以在48小时内在单个桌面GPU(1080 Ti)上进行训练。

英文摘要:

Robust multi-agent trajectory prediction is essential for the safe control of robotic systems. A major challenge is to efficiently learn a representation that approximates the true joint distribution of contextual, social, and temporal information to enable planning. We propose Latent Variable Sequential Set Transformers which are encoder-decoder architectures that generate scene-consistent multi-agent trajectories. We refer to these architectures as "AutoBots". The encoder is a stack of interleaved temporal and social multi-head self-attention (MHSA) modules which alternately perform equivariant processing across the temporal and social dimensions. The decoder employs learnable seed parameters in combination with temporal and social MHSA modules allowing it to perform inference over the entire future scene in a single forward pass efficiently. AutoBots can produce either the trajectory of one ego-agent or a distribution over the future trajectories for all agents in the scene. For the single-agent prediction case, our model achieves top results on the global nuScenes vehicle motion prediction leaderboard, and produces strong results on the Argoverse vehicle prediction challenge. In the multi-agent setting, we evaluate on the synthetic partition of TrajNet++ dataset to showcase the model's socially-consistent predictions. We also demonstrate our model on general sequences of sets and provide illustrative experiments modelling the sequential structure of the multiple strokes that make up symbols in the Omniglot data. A distinguishing feature of AutoBots is that all models are trainable on a single desktop GPU (1080 Ti) in under 48h.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑