当前位置:
X-MOL 学术
›
arXiv.cs.MA
›
论文详情
Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
Altruistic Decision-Making for Autonomous Driving with Sparse Rewards
arXiv - CS - Multiagent Systems Pub Date : 2020-07-14 , DOI: arxiv-2007.07182 Jack Geary, Henry Gouk
arXiv - CS - Multiagent Systems Pub Date : 2020-07-14 , DOI: arxiv-2007.07182 Jack Geary, Henry Gouk
In order to drive effectively, a driver must be aware of how they can expect
other vehicles' behaviour to be affected by their decisions, and also how they
are expected to behave by other drivers. One common family of methods for
addressing this problem of interaction are those based on Game Theory. Such
approaches often make assumptions about leaders and followers in an interaction
which can result in conflicts arising when vehicles do not agree on the
hierarchy, resulting in sub-optimal behaviour. In this work we define a
measurement for the incidence of conflicts, Area of Conflict (AoC), for a given
interactive decision-making model. Furthermore, we propose a novel
decision-making method that reduces this value compared to an existing approach
for incorporating altruistic behaviour. We verify our theoretical analysis
empirically using a simulated lane-change scenario.
中文翻译:
具有稀疏奖励的自动驾驶的利他决策
为了有效驾驶,驾驶员必须了解他们如何预期其他车辆的行为会受到他们的决定的影响,以及其他驾驶员对他们的行为有何预期。解决这个交互问题的一个常见方法系列是基于博弈论的方法。这种方法通常对交互中的领导者和追随者做出假设,当车辆在等级制度上不一致时,可能会导致冲突,从而导致次优行为。在这项工作中,我们为给定的交互式决策模型定义了冲突发生率的度量,即冲突区域 (AoC)。此外,我们提出了一种新的决策方法,与结合利他行为的现有方法相比,该方法降低了该值。
更新日期:2020-07-15
中文翻译:
具有稀疏奖励的自动驾驶的利他决策
为了有效驾驶,驾驶员必须了解他们如何预期其他车辆的行为会受到他们的决定的影响,以及其他驾驶员对他们的行为有何预期。解决这个交互问题的一个常见方法系列是基于博弈论的方法。这种方法通常对交互中的领导者和追随者做出假设,当车辆在等级制度上不一致时,可能会导致冲突,从而导致次优行为。在这项工作中,我们为给定的交互式决策模型定义了冲突发生率的度量,即冲突区域 (AoC)。此外,我们提出了一种新的决策方法,与结合利他行为的现有方法相比,该方法降低了该值。