A Game-Theoretic Strategy-Aware Interaction Algorithm with Validation on Real Traffic Data

Sun, Liting; Cai, Mu; Zhan, Wei; Tomizuka, Masayoshi

doi:10.1109/iros45743.2020.9340988

Cited by 12 publications

(10 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…the agent type value for each model when the strategy matched the observation. The overall numbers in the table are in line with the converging consensus from recent literature that there is heterogeneity in driving behavior (Sarkar and Czarnecki 2021;Sun et al 2020). However, a major takeaway is that for non-strategic models, automata models show much higher accuracy thereby reflecting high alignment with human driving behavior compared to the maxmax model.…”

Section: Naturalistic Datasupporting

confidence: 83%

“…As AVs integrate into human traffic, there has been a move from a predict-and-plan approach of behavior planning to a more strategic approach where the problem of behavior planning of an AV is set up as a non-zero sum game between road users and the AV; and such models have shown efficacy in simulation of different traffic scenarios (Fisac et al 2019;Tian et al 2018). However, when game theoretic models are evaluated on naturalistic human driving data, studies have shown that human driving behavior is diverse, and therefore developing a unifying framework that can both model the diversity of human driving behavior as well as plan a response from the perspective of an AV is challenging (Sarkar and Czarnecki 2021;Sun et al 2020).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Generalized dynamic cognitive hierarchy models for strategic driving behavior

Sarkar¹,

Larson²,

Czarnecki³

2021

Preprint

View full text Add to dashboard Cite

While there has been an increasing focus on the use of game theoretic models for autonomous driving, empirical evidence shows that there are still open questions around dealing with the challenges of common knowledge assumptions as well as modeling bounded rationality. To address some of these practical challenges, we develop a framework of generalized dynamic cognitive hierarchy for both modelling naturalistic human driving behavior as well as behavior planning for autonomous vehicles (AV). This framework is built upon a rich model of level-0 behavior through the use of automata strategies, an interpretable notion of bounded rationality through safety and maneuver satisficing, and a robust response for planning. Based on evaluation on two large naturalistic datasets as well as simulation of critical traffic scenarios, we show that i) automata strategies are well suited for level-0 behavior in a dynamic level-k framework, and ii) the proposed robust response to a heterogeneous population of strategic and non-strategic reasoners can be an effective approach for game theoretic planning in AV.

show abstract

Section: Naturalistic Datasupporting

confidence: 83%

Section: Introductionmentioning

confidence: 99%

Generalized dynamic cognitive hierarchy models for strategic driving behavior

Sarkar¹,

Larson²,

Czarnecki³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…the driver becomes attentive when sees a pedestrian at the edge of the road. Other interesting methods in this topic can be found in [76], [77], [78], [79].…”

Section: Infocommunications Journalmentioning

confidence: 99%

Traffic Swarm Behaviour: Machine Learning and Game Theory in Behaviour Analysis

Hollósi¹,

Lukovszki²,

Bancsics³

et al. 2021

Infocommunications journal

View full text Add to dashboard Cite

High density traffic on highways and city streets consists of endless interactions among participants. These interactions and the corresponding behaviours have great impact not only on throughput of traffic but also on safety, comfort and economy. Because of this, there is a great interest in deeper understanding of these interactions and concluding the impacts on traffic participants. This paper explores and maps the world of traffic behaviour analysis, especially researches focusing on groups of vehicles called traffic swarm, while presents the state-of-the-art methods and algorithms. The conclusion of this paper states that there are special areas of traffic behaviour analysis which have great research potential in the near future to describe traffic behaviour in more detail than present methods.

show abstract

“…Such planners, referred to as strategic planners, view other road users in the vicinity as agents playing a game, and the AV chooses an action based on a game solution, for example, a Nash equilibrium. Such models have shown to be effective in simulation, and also have been evaluated against naturalistic human driving behavior [7], [8]. On the other hand, evaluation of safety is also arguably a multi-agent problem, based on the idea that the outcome of a traffic situation depends on the assumptions traffic agents have over each other as well as the collective behavior based on those assumptions.…”

Section: Introductionmentioning

confidence: 99%

“…The process of calculating the solution and executing the strategies is referred to as playing or solving the game. Some of the solution concepts that have been proposed in the literature for strategic planning in AVs include Nash equilibrium [5], [7], [23], [24], Stackelberg equilibrium [6], Qlk model [1]- [3], [7], and Pareto optimality [8].…”

Section: Introductionmentioning

confidence: 99%

I Know You Can't See Me: Dynamic Occlusion-Aware Safety Validation of Strategic Planners for Autonomous Vehicles Using Hypergames

Kahn¹,

Sarkar²,

Czarnecki³

2021

Preprint

View full text Add to dashboard Cite

A particular challenge for both autonomous and human driving is dealing with risk associated with dynamic occlusion, i.e., occlusion caused by other vehicles in traffic. Based on the theory of hypergames, we develop a novel multiagent dynamic occlusion risk (DOR) measure for assessing situational risk in dynamic occlusion scenarios. Furthermore, we present a white-box, scenario-based, accelerated safety validation framework for assessing safety of strategic planners in AV. Based on evaluation over a large naturalistic database, our proposed validation method achieves a 4000% speedup compared to direct validation on naturalistic data, a more diverse coverage, and ability to generalize beyond the dataset and generate commonly observed dynamic occlusion crashes in traffic in an automated manner.

show abstract

A Game-Theoretic Strategy-Aware Interaction Algorithm with Validation on Real Traffic Data

Cited by 12 publications

References 16 publications

Generalized dynamic cognitive hierarchy models for strategic driving behavior

Generalized dynamic cognitive hierarchy models for strategic driving behavior

Traffic Swarm Behaviour: Machine Learning and Game Theory in Behaviour Analysis

I Know You Can't See Me: Dynamic Occlusion-Aware Safety Validation of Strategic Planners for Autonomous Vehicles Using Hypergames

Contact Info

Product

Resources

About