A Hybrid Control Design for Autonomous Vehicles at Uncontrolled Crosswalks

Kapania, Nitin R.; Govindarajan, Vijay; Borrelli, Francesco; Gerdes, J. Christian

doi:10.1109/ivs.2019.8814116

Cited by 23 publications

(15 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The model may also be useful as a component in algorithms for real-time sensor data interpretation. Making use of models of pedestrian behavior in automated vehicle algorithms is an active area of research, but so far the models used have been relatively simplistic (Camara et al, 2020;Jayaraman et al, 2021;Kapania et al, 2019). Another important role of human behavior models in vehicle development is as agents in simulation environments for virtual testing (Behbahani et al, 2019;Camara et al, 2020;.…”

Section: Applied Implicationsmentioning

confidence: 99%

“…The majority of the research in this area has been observational (Lobjois & Cavallo, 2007;Schneemann & Gohl, 2016;Varhelyi, 1998), but some previous mathematical models exist. In the context of large-scale traffic simulation, logistic regression models have long been used to model pedestrian "gap acceptance" between vehicles in a stream of traffic (Brewer et al, 2006;Schroeder, 2008;Yannis et al, 2013), and the use of such models in automated vehicle algorithms has also been proposed (Jayaraman et al, 2021;Kapania et al, 2019). However, these models are limited to a discrete acceptance/rejection decision per gap, and do not account for the timing of roadcrossing decisions, which has implications for traffic flow and acceptance of automated vehicles (Dey et al, 2020;Lee et al, 2020;.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Variable-Drift Diffusion Models of Pedestrian Road-Crossing Decisions

et al. 2021

View full text Add to dashboard Cite

Human behavior and interaction in road traffic is highly complex, with many open scientific questions of high applied importance, not least in relation to recent development efforts toward automated vehicles. In parallel, recent decades have seen major advances in cognitive neuroscience models of human decision-making, but these models have mainly been applied to simplified laboratory tasks. Here, we demonstrate how variable-drift extensions of drift diffusion (or evidence accumulation) models of decision-making can be adapted to the mundane yet non-trivial scenario of a pedestrian deciding if and when to cross a road with oncoming vehicle traffic. Our variable-drift diffusion models provide a mechanistic account of pedestrian road-crossing decisions, and how these are impacted by a variety of sensory cues: time and distance gaps in oncoming vehicle traffic, vehicle deceleration implicitly signaling intent to yield, as well as explicit communication of such yielding intentions. We conclude that variable-drift diffusion models not only hold great promise as mechanistic models of complex real-world decisions, but that they can also serve as applied tools for improving road traffic safety and efficiency.

show abstract

Section: Applied Implicationsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Variable-Drift Diffusion Models of Pedestrian Road-Crossing Decisions

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The model may also be useful as a component in algorithms for real-time sensor data interpretation. Making use of models of pedestrian behaviour in automated vehicle algorithms is an active area of research, but so far the mod-els used have been relatively simplistic [9,29,30]. Another important role of human behavior models in vehicle development is as agents in simulation environments for virtual testing [1,9,41].…”

Section: Applied Implicationsmentioning

confidence: 99%

“…The majority of the research in this area has been observational [35,59,67], but some previous mathematical models exist. In the context of large-scale traffic simulation, logistic regression models have long been used to model pedestrian 'gap acceptance' between vehicles in a stream of traffic [4,62,72], and the use of such models in automated vehicle algorithms has also been proposed [29,30]. However, these models are limited to a discrete acceptance/rejection decision per gap, and do not account for the timing of road-crossing decisions, which has implications for traffic flow and acceptance of automated vehicles [12,34,41].…”

Section: Introductionmentioning

confidence: 99%

Variable-drift diffusion models of pedestrian road-crossing decisions

Pekkanen¹,

Giles²,

Lee³

et al. 2021

Preprint

View full text Add to dashboard Cite

Human behavior and interaction in road traffic is highly complex, with many open scientifi?c questions of high applied importance, not least in relation to recent development efforts toward automated vehicles. In parallel, recent decades have seen major advances in cognitive neuroscience models of human decision-making, but these models have mainly been applied to simplified laboratory tasks. Here, we demonstrate how variable-drift extensions of drift diffusion (or evidence accumulation) models of decision-making can be adapted to the mundane yet non-trivial scenario of a pedestrian deciding if and when to cross a road with oncoming vehicle traffic. Our variable-drift diffusion models provide a mechanistic account of pedestrian road-crossing decisions, and how these are impacted by a variety of sensory cues: time and distance gaps in oncoming vehicle traffic, vehicle deceleration implicitly signaling intent to yield, as well as explicit communication of such yielding intentions. We conclude that variable-drift diffusion models not only hold great promise as mechanistic models of complex real-world decisions, but that they can also serve as applied tools for improving road traffic safety and efficiency.

show abstract

“…An ontology-based DMS was introduced in [21] and [22] with the assumption that other vehicle's intended driving direction is observable. Finally, another noticeable RB solution for AV's DMS at unprotected crosswalk was delivered in [23]. Still these methods were demonstrated only for simple scenarios.…”

mentioning

confidence: 99%

Rule-Based Decision-Making System for Autonomous Vehicles at Intersections with Mixed Traffic Environment

Aksjonov

Kyrki

2021

2021 IEEE International Intelligent Transportation Systems Conference (ITSC)

View full text Add to dashboard Cite

Before autonomous vehicles are widely spread, they will share the roads with non-autonomous cars. Furthermore, to ensure functional safety of the self-driving cars, the cause of decision-making and control algorithms' failure must be precisely identified. Rule-based methods are promising solutions due to their transparency and comprehensibility. In this paper, a rule-based decision-making system for autonomous vehicles solving a challenge of complex intersection with mixed driving environment is proposed. The system is designed to prioritize road safety and avoid collision with other road users at any cost. The proposed algorithm relies only on available on-board perception and localization sensors, allowing the automated car to operate among human-driven vehicle and without vehicle-to-vehicle communication technology. The system is validated in a simulation study on cross-intersection, where the ego vehicle deals with multiple cars arriving from different sides of the road. The results demonstrate algorithm's robustness and effectiveness under multiple scenarios, when neither intention nor trajectory of other traffic participants is known. Thus, the proposed solution is also potentially applicable to other types of intersections with different traffic rules. I. INTRODUCTIONRapidly evolving autonomous vehicle (AV) and intelligent transportation technologies are set to significantly change the way of human and goods transportation. In addition to comfort and efficiency, AVs provide a vital improvement in traffic safety. Furthermore, the technology will allow people to dedicate their time to more pleasant activities instead of driving in traffic congestion. Yet, the first AVs will collaborate with human-driven vehicles. Thus, development of a decision-making system (DMS), which mimics experienced human driver and allows AV's to coexist together with non-AVs in mixed ecosystem, poses a great challenge.The learning-based algorithms that rely on quality data tend to be efficient in DMS design. These algorithms, however, induce problems for practical application, because they serve as a black box. Therefore, they are challenged with functional safety compatibility. Rule-based (RB) methods, despite being more complicated, are transparent and clearly defined by set of rules and equations, meaning that the reasons for system failure can be easily observed and even eliminated in advance [1].An intersection crossing is one of the most challenging tasks for AV. Among the most popular automation methods to tackle this problem are RB, optimization, hybrid,

show abstract

A Hybrid Control Design for Autonomous Vehicles at Uncontrolled Crosswalks

Cited by 23 publications

References 17 publications

Variable-Drift Diffusion Models of Pedestrian Road-Crossing Decisions

Variable-Drift Diffusion Models of Pedestrian Road-Crossing Decisions

Variable-drift diffusion models of pedestrian road-crossing decisions

Rule-Based Decision-Making System for Autonomous Vehicles at Intersections with Mixed Traffic Environment

Contact Info

Product

Resources

About