見えるロボット：人間の姿勢を活用した軌道予測
Robots That Can See: Leveraging Human Pose for Trajectory Prediction
人間の位置・頭の向き・3D骨格キーポイントを入力に、Transformerで人間の将来軌道を予測する手法を提案し、不確実性を捉えつつベンチマークで最高性能を達成した。
著者: Tim Salzmann, Lewis Chiang, Markus Ryll, Dorsa Sadigh, Carolina Parada, Alex Bewley
分類: cs.RO, cs.CV, cs.HC, cs.LG
原文アブストラクト
Anticipating the motion of all humans in dynamic environments such as homes and offices is critical to enable safe and effective robot navigation. Such spaces remain challenging as humans do not follow strict rules of motion and there are often multiple occluded entry points such as corners and doors that create opportunities for sudden encounters. In this work, we present a Transformer based architecture to predict human future trajectories in human-centric environments from input features including human positions, head orientations, and 3D skeletal keypoints from onboard in-the-wild sensory information. The resulting model captures the inherent uncertainty for future human trajectory prediction and achieves state-of-the-art performance on common prediction benchmarks and a human tracking dataset captured from a mobile robot adapted for the prediction task. Furthermore, we identify new agents with limited historical data as a major contributor to error and demonstrate the complementary nature of 3D skeletal poses in reducing prediction error in such challenging scenarios.
