Safe Stop Trajectory Planning for Highly Automated Vehicles: An Optimal Control Problem Formulation

Svensson, Lars E. O.; Masson, Lola; Mohan, Naveen; Ward, Erik; Brenden, Anna Pernestål; Feng, Lei; Törngren, Martin

doi:10.1109/ivs.2018.8500536

Cited by 28 publications

(36 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Systems monitoring heart rate, pupil diameter and gaze may be able to detect when a person is not able to respond to a takeover situation (Alrefaie et al, 2019). These systems could potentially work in conjunction with an emergency fall back of safe stop or safe manoeuvrer, where the driver is not ready (Svensson, 2018). However, even where drivers are alerted to a vehicle handover via auditory/visual and haptic warning messages, drivers struggle to regain attention to driving following a period of automated driving (Bloomberg, 2017).…”

Section: Human Factors-riskmentioning

confidence: 99%

Legal issues in automated vehicles: critically considering the potential role of consent and interactive digital interfaces

Pattinson

Chen

Basu

2020

Humanit Soc Sci Commun

View full text Add to dashboard Cite

Some of the first ‘automated’ vehicles to be deployed on our roads will require a system of shared driving with a human driver. While this creates technical and operational challenges, the law must also facilitate such a transfer. One method may be to obtain the driver’s consent to share operational responsibility and to delineate legal responsibility between vehicle and driver in the event of an accident. Consent is a voluntary agreement where an individual is aware of the potential consequences of their consent, including the risks. The driver of a partially automated vehicle must be informed of potential risks before giving consent to share operational responsibility. This paper will refer to the inherent dangers associated with shared operational responsibility, in particular where there has been a request for the driver to take back control from the automated vehicle during the journey. Drivers are likely to experience delay in regaining situational awareness, making such operational transfers hazardous. It is argued that where an interactive digital interface is used to convey information, such as driver responsibility, risk and legal terms, drivers may fail to sufficiently process such communications due to fundamental weaknesses in human–machine interaction. The use of an interactive digital interface alone may be inadequate to effectively communicate information to drivers. If the problems identified are not addressed, it is argued that driver consent may be inconsequential, and fail to facilitate a predicable demarcation of legal responsibility between automated vehicles and drivers. Ongoing research into automated vehicle driver training is considered as part of the preparation required to design driver education to a level whereby drivers may be able to sufficiently understand the responsibilities involved in operating a partially automated vehicle, which has implications for future driver training, licensing and certification.

show abstract

Section: Human Factors-riskmentioning

confidence: 99%

Legal issues in automated vehicles: critically considering the potential role of consent and interactive digital interfaces

Pattinson

Chen

Basu

2020

Humanit Soc Sci Commun

View full text Add to dashboard Cite

show abstract

“…An intuitive way to reduce suboptimality of the trajectories in the set is to solve the two-point boundary value problem offline, using a dynamic model. This method has been demonstrated successfully in several previous works [5], [6]. However, this approach prohibits online model adaptation, since the trajectories in the pre-computed library are computed based on a static vehicle representation.…”

Section: Related Workmentioning

confidence: 99%

“…The non-adaptive trajectory optimization assumes a static friction estimate µ asm = 0.8 throughout, while our proposed SAA-RTI reestimates this value and accordingly adapts input constraints U t (µ t ) (see Fig. 1) in (5). To mimic the convergence time of a friction estimation algorithm, we introduce a time delay of 100ms before the correct value of µ is applied in SAA-RTI.…”

Section: A Adaptive Vs Non-adaptive Trajectory Optimizationmentioning

confidence: 99%

Adaptive Trajectory Planning and optimization at Limits of Handling

Svensson

Bujarbaruah

Kapania

et al. 2019

2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Self Cite

View full text Add to dashboard Cite

In this paper, we tackle the problem of trajectory planning and control of a vehicle under locally varying traction limitations, in the presence of suddenly appearing obstacles. We employ concepts from adaptive model predictive control for run-time adaptation of tire force constraints that are imposed by local traction conditions. To solve the resulting optimization problem for real-time control synthesis with such time varying constraints, we propose a novel numerical scheme based on Real Time Iteration Sequential Quadratic Programming (RTI-SQP), which we call Sampling Augmented Adaptive RTI (SAA-RTI). Sampling augmentation of conventional RTI-SQP provides additional feasible candidate trajectories for warmstarting the optimization procedure. Thus, the proposed SAA-RTI algorithm enables real time constraint adaptation and reduces sensitivity to local minima. Through extensive numerical simulations we demonstrate that our method increases the vehicle's capacity to avoid accidents in scenarios with unanticipated obstacles and locally varying traction, compared to equivalent non-adaptive control schemes and traditional planning and tracking approaches.

show abstract

“…For road vehicles, Werling et al [34] proposed an optimal trajectory generation method, with which velocity maintenance, merging, following, stopping and a reactive collision avoidance functionality were achieved. In [35] a real-time safe stop trajectory planning algorithm, based on selection from a precomputed set of trajectories has been developed. Several papers deal with the selection of the velocity of autonomous vehicles, which has relevance in the problem of intersection scenarios.…”

Section: Introductionmentioning

confidence: 99%

The Design of Performance Guaranteed Autonomous Vehicle Control for Optimal Motion in Unsignalized Intersections

Németh

Gáspár

2021

Applied Sciences

View full text Add to dashboard Cite

The design of the motion of autonomous vehicles in non-signalized intersections with the consideration of multiple criteria and safety constraints is a challenging problem with several tasks. In this paper, a learning-based control solution with guarantees for collision avoidance is proposed. The design problem is formed in a novel way through the division of the control problem, which leads to reduced complexity for achieving real-time computation. First, an environment model for the intersection was created based on a constrained quadratic optimization, with which guarantees on collision avoidance can be provided. A robust cruise controller for the autonomous vehicle was also designed. Second, the environment model was used in the training process, which was based on a reinforcement learning method. The goal of the training was to improve the economy of autonomous vehicles, while guaranteeing collision avoidance. The effectiveness of the method is presented through simulation examples in non-signalized intersection scenarios with varying numbers of vehicles.

show abstract

Safe Stop Trajectory Planning for Highly Automated Vehicles: An Optimal Control Problem Formulation

Cited by 28 publications

References 17 publications

Legal issues in automated vehicles: critically considering the potential role of consent and interactive digital interfaces

Legal issues in automated vehicles: critically considering the potential role of consent and interactive digital interfaces

Adaptive Trajectory Planning and optimization at Limits of Handling

The Design of Performance Guaranteed Autonomous Vehicle Control for Optimal Motion in Unsignalized Intersections

Contact Info

Product

Resources

About