Pre-training on Synthetic Driving Data for Trajectory Prediction

[PDF] arxiv.org

Adaptive Human Trajectory Prediction via Latent Corridors

N Thakkar, K Mangalam, A Bajcsy, J Malik - arXiv preprint arXiv …, 2023 - arxiv.org
Human trajectory prediction is typically posed as a zero-shot generalization problem: a
predictor is learnt on a dataset of human motion in training scenes, and then deployed on …
相关文章 所有 2 个版本
[PDF] arxiv.org

Cohere3D: Exploiting Temporal Coherence for Unsupervised Representation Learning of Vision-based Autonomous Driving

Y Xie, H Chen, GP Meyer, YJ Lee, EM Wolff… - arXiv preprint arXiv …, 2024 - arxiv.org
Due to the lack of depth cues in images, multi-frame inputs are important for the success of
vision-based perception, prediction, and planning in autonomous driving. Observations from …
相关文章 所有 3 个版本
[PDF] arxiv.org

A General Calibrated Regret Metric for Detecting and Mitigating Human-Robot Interaction Failures

K Nakamura, R Tian, A Bajcsy - arXiv preprint arXiv:2403.04745, 2024 - arxiv.org
Robot decision-making increasingly relies on expressive data-driven human prediction
models when operating around people. While these models are known to suffer from …
相关文章 所有 2 个版本