Trajectron++: 異種データを活用した動的に実行可能な軌道予測
Trajectron++: Dynamically-Feasible Trajectory Forecasting With Heterogeneous Data
エージェントの動力学やセマンティックマップなどの異種データを組み込み、ロボットの計画・制御と連携可能なグラフ構造の再帰モデルによる軌道予測手法を提案した。
著者: Tim Salzmann, Boris Ivanovic, Punarjay Chakravarty, Marco Pavone
分類: cs.RO, cs.HC, cs.LG
原文アブストラクト
Reasoning about human motion is an important prerequisite to safe and socially-aware robotic navigation. As a result, multi-agent behavior prediction has become a core component of modern human-robot interactive systems, such as self-driving cars. While there exist many methods for trajectory forecasting, most do not enforce dynamic constraints and do not account for environmental information (e.g., maps). Towards this end, we present Trajectron++, a modular, graph-structured recurrent model that forecasts the trajectories of a general number of diverse agents while incorporating agent dynamics and heterogeneous data (e.g., semantic maps). Trajectron++ is designed to be tightly integrated with robotic planning and control frameworks; for example, it can produce predictions that are optionally conditioned on ego-agent motion plans. We demonstrate its performance on several challenging real-world trajectory forecasting datasets, outperforming a wide array of state-of-the-art deterministic and generative methods.
