arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1901.00898cs.LGcs.AIcs.CVstat.ML
收藏

基于强化学习和视觉的紧急碰撞缓解

Imminent Collision Mitigation with Reinforcement Learning and Vision

Oxford Robotics Institute(牛津机器人研究所);University of Oxford(牛津大学)

Horia Porav, Paul Newman

摘要:

这项工作研究了强化学习在减少道路碰撞的严重程度,通过控制速度和转向的情况下,接触是迫在眉睫的作用。我们构建了一个模型,给定摄像机图像作为输入,能够学习和预测障碍物,汽车和行人的动态,并使用此模型训练我们的政策。控制制动和转向的两种策略与基线进行比较,其中所采取的唯一行动是(传统的)直线制动。这两种策略使用两种不同的奖励结构进行训练,一种是任何和所有碰撞都会产生固定的惩罚,第二种是根据已经建立的伤害严重程度的delta-v模型计算惩罚。结果表明,这两种策略都超过了基线的性能,使用损伤模型训练的策略具有最高的性能。

英文摘要:

This work examines the role of reinforcement learning in reducing the severity of on-road collisions by controlling velocity and steering in situations in which contact is imminent. We construct a model, given camera images as input, that is capable of learning and predicting the dynamics of obstacles, cars and pedestrians, and train our policy using this model. Two policies that control both braking and steering are compared against a baseline where the only action taken is (conventional) braking in a straight line. The two policies are trained using two distinct reward structures, one where any and all collisions incur a fixed penalty, and a second one where the penalty is calculated based on already established delta-v models of injury severity. The results show that both policies exceed the performance of the baseline, with the policy trained using injury models having the highest performance.

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。

↑