arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2106.06920cs.ROcs.LG
收藏

导航中多模态场景兼容的用户意图估计

Multi-modal Scene-compliant User Intention Estimation in Navigation

University of Technology Sydney(悉尼科技大学)

Kavindie Katuwandeniya, Stefan H. Kiss, Lei Shi, Jaime Valls Miro

摘要:

本文提出了一个多模态框架来生成用户意图分布,当操作移动车辆。该模型从过去观察到的轨迹中学习,并利用从视觉环境中获得的可通行性信息来产生一组未来轨迹,适合直接嵌入到移动代理上的感知-动作共享控制策略中,或者作为安全层来监督车辆的谨慎操作。我们的解决方案基于一个有条件的生成对抗网络与长短期记忆细胞捕捉轨迹分布的条件下,过去的轨迹,进一步融合来自视觉分割与卷积神经网络的遍历概率。所提出的数据驱动框架导致预测轨迹(与地面实况相比)的误差显着减少,而文献中的可比策略(例如,Social-GAN)未能考虑代理过去历史以外的信息。实验是在一个数据集上进行的,该数据集是用一个构建在开源城市驾驶模拟器CARLA上的自定义轮椅模型收集的,这也证明了所提出的框架可以用于一个小的、未注释的数据集。

英文摘要:

A multi-modal framework to generate user intention distributions when operating a mobile vehicle is proposed in this work. The model learns from past observed trajectories and leverages traversability information derived from the visual surroundings to produce a set of future trajectories, suitable to be directly embedded into a perception-action shared control strategy on a mobile agent, or as a safety layer to supervise the prudent operation of the vehicle. We base our solution on a conditional Generative Adversarial Network with Long-Short Term Memory cells to capture trajectory distributions conditioned on past trajectories, further fused with traversability probabilities derived from visual segmentation with a Convolutional Neural Network. The proposed data-driven framework results in a significant reduction in error of the predicted trajectories (versus the ground truth) from comparable strategies in the literature (e.g. Social-GAN) that fail to account for information other than the agent's past history. Experiments were conducted on a dataset collected with a custom wheelchair model built onto the open-source urban driving simulator CARLA, proving also that the proposed framework can be used with a small, un-annotated dataset.

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。

↑