Turning the corner: improved intersection control for autonomous vehicles

Dresner, Kurt; Stone, Peter

doi:10.1109/ivs.2005.1505140

Cited by 12 publications

(5 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fewer researchers have tackled the intersection management task for much more challenging mixed traffic and especially scenarios with a vast majority of HDVs, which will be prevalent in the near future. Dresner and Stone extended their cell reservation system from previous works by different fallback modes in [22]. Those modes use dynamically controlled traffic light phases to allow safe crossing of HDVs, which still provides comparable efficiency results at a rate of 5 % HDVs.…”

Section: Related Workmentioning

confidence: 99%

Cooperative Behavior Planning for Automated Driving Using Graph Neural Networks

Klimke

Völz

Buchholz

2022

2022 IEEE Intelligent Vehicles Symposium (IV)

View full text Add to dashboard Cite

Urban intersections are prone to delays and inefficiencies due to static precedence rules and occlusions limiting the view on prioritized traffic. Existing approaches to improve traffic flow, widely known as automatic intersection management systems, are mostly based on non-learning reservation schemes or optimization algorithms. Machine learning-based techniques show promising results in planning for a single ego vehicle. This work proposes to leverage machine learning algorithms to optimize traffic flow at urban intersections by jointly planning for multiple vehicles. Learning-based behavior planning poses several challenges, demanding for a suited input and output representation as well as large amounts of ground-truth data. We address the former issue by using a flexible graph-based input representation accompanied by a graph neural network. This allows to efficiently encode the scene and inherently provide individual outputs for all involved vehicles. To learn a sensible policy, without relying on the imitation of expert demonstrations, the cooperative planning task is considered as a reinforcement learning problem. We train and evaluate the proposed method in an open-source simulation environment for decision making in automated driving. Compared to a first-in-first-out scheme and traffic governed by static priority rules, the learned planner shows a significant gain in flow rate, while reducing the number of induced stops. In addition to synthetic simulations, the approach is also evaluated based on real-world traffic data taken from the publicly available inD dataset.

show abstract

Section: Related Workmentioning

confidence: 99%

Cooperative Behavior Planning for Automated Driving Using Graph Neural Networks

Klimke

Völz

Buchholz

2022

2022 IEEE Intelligent Vehicles Symposium (IV)

View full text Add to dashboard Cite

show abstract

“…Finally, we review literature concerning reservation-based algorithms [15]- [18], where communicating vehicles reserve some sort of space-time slots by requesting them via a supervisor. It must be guaranteed that the space-time slots are not occupied by more than one vehicle in order to ensure safety.…”

Section: Introductionmentioning

confidence: 99%

“…It must be guaranteed that the space-time slots are not occupied by more than one vehicle in order to ensure safety. In [15]- [17], reservation-based algorithms are applied to intersections; [15] in particular divides the intersection into tiles which can be allocated to communicating vehicles. Marinescu et al [18] implement a slot-based approach for the merging of on-ramp traffic.…”

Section: Introductionmentioning

confidence: 99%

Negotiation of drivable areas of cooperative vehicles for conflict resolution

Manzinger

Althoff

2017

2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC)

View full text Add to dashboard Cite

We address the problem of cooperative conflict resolution for multi-vehicle motion planning in mixed-traffic scenarios, where automated and manually-driven vehicles coexist. We propose a novel solution based on reachability analysis, which provides the drivable area of each collaborative traffic participant. Overlapping drivable areas are redistributed so that each traffic participant receives an individual area for motion planning. We do not stipulate a specific method for predicting the future motion of non-communicating traffic participants. Furthermore, uncertainties in the initial states of the cooperative vehicles, e.g. due to sensor noise, can be easily integrated. A byproduct of our approach is that collaborative groups can be automatically found by identifying conflicting drivable areas; if no conflict exists, collaboration becomes unnecessary. We demonstrate the redistribution of drivable areas with two numerical examples.

show abstract

“…There are substantial efforts devoted to this problem proceeding from various angles. See, for example, [5], [7], [8], [9], [10], [12] and the references cited therein.The traffic control signals at the intersections of a road network are crucial for regulating traffic flow. Except in situations involving accidents, most delays occur at the intersections.…”

Section: Introductionmentioning

confidence: 99%

Modeling and Solution for Traffic Network Signal Optimization

2009

2009 IITA International Conference on Services Science, Management and Engineering

View full text Add to dashboard Cite

This paper discusses the optimal traffic control signal setting for a rectangular road traffic network with left turn forbidden. By introducing the concepts of synchronization rate and non-synchronization degree, a mathematical model is constructed and an optimization problem is posed. Then, a new iterative algorithm is developed to solve this optimal traffic control signal setting problem. Convergence properties for this iterative algorithm are established.

show abstract

Turning the corner: improved intersection control for autonomous vehicles

Cited by 12 publications

References 2 publications

Cooperative Behavior Planning for Automated Driving Using Graph Neural Networks

Cooperative Behavior Planning for Automated Driving Using Graph Neural Networks

Negotiation of drivable areas of cooperative vehicles for conflict resolution

Modeling and Solution for Traffic Network Signal Optimization

Contact Info

Product

Resources

About