A Belief State Planner for Interactive Merge Maneuvers in Congested Traffic

Hubmann, Constantin; Schulz, Jens; Xu, Gavin; Althoff, Daniel; Stiller, Christoph

doi:10.1109/itsc.2018.8569729

Cited by 70 publications

(67 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Future work involves using more sophisticated techniques to estimate driver behavior. Other algorithms to learn belief state policies could be considered, as well as a direct comparison with online POMDP solvers [3]. Although our RL agent learned more efficient policies, an online planner may provide greater robustness.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Cooperation-Aware Reinforcement Learning for Merging in Dense Traffic

Bouton

Nakhaei

Fujimura

et al. 2019

2019 IEEE Intelligent Transportation Systems Conference (ITSC)

View full text Add to dashboard Cite

Decision making in dense traffic can be challenging for autonomous vehicles. An autonomous system only relying on predefined road priorities and considering other drivers as moving objects will cause the vehicle to freeze and fail the maneuver. Human drivers leverage the cooperation of other drivers to avoid such deadlock situations and convince others to change their behavior. Decision making algorithms must reason about the interaction with other drivers and anticipate a broad range of driver behaviors. In this work, we present a reinforcement learning approach to learn how to interact with drivers with different cooperation levels. We enhanced the performance of traditional reinforcement learning algorithms by maintaining a belief over the level of cooperation of other drivers. We show that our agent successfully learns how to navigate a dense merging scenario with less deadlocks than with online planning methods.

show abstract

Section: Discussionmentioning

confidence: 99%

“…These approaches can scale to large environments and continuous state spaces, but they still suffer from the curse of dimensionality. The computational complexity associated with dense traffic scenarios limits the planning to short time horizons [3], [6] or limit the number of vehicles considered [4], [5].…”

Section: Introductionmentioning

confidence: 99%

Cooperation-Aware Reinforcement Learning for Merging in Dense Traffic

Bouton

Nakhaei

Fujimura

et al. 2019

2019 IEEE Intelligent Transportation Systems Conference (ITSC)

View full text Add to dashboard Cite

show abstract

“…Classical approaches that subdivide the motion planning into behavior and trajectory planning [2] have the advantage of good computational tractability and modularity [4]. However, through the neglected feedback, the set of solution is reduced.…”

Section: A Related Workmentioning

confidence: 99%

“…Finally, approaches based on Markov Decision Processes use learning data and mostly reinforcement learning [5] or related methods [4] to learn an appropriate control law guiding the ego vehicle through the merging scenario. The approaches of this category holistically solve the problem, inherently accounting for uncertainties.…”

Section: A Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Risk and Comfort Optimizing Motion Planning Scheme for Merging Scenarios

Müller

Buchholz

2019

2019 IEEE Intelligent Transportation Systems Conference (ITSC)

View full text Add to dashboard Cite

Motion planning for merging scenarios accounting for measurement and prediction uncertainties is a major challenge on the way to autonomous driving. Classical methods subdivide the motion planning into behavior and trajectory planning, thus narrowing down the solution set. Hence, in complex merging scenarios, no suitable solution might be found. In this work, we present a planning scheme that solves behavior and trajectory planning together by exploring all possible decision options. A safety strategy is implemented and the risk of violating a safety constraint is minimized as well as the jerk to feature a risk and comfort optimal trajectory. To mitigate the injection of noise into the actual trajectory, a new analytical trajectory generation method is derived and its optimality is proven. The decision capability is evaluated through Monte-Carlo simulation. Furthermore, the calculation time is evaluated showing the real-time capability of our approach.

show abstract

TMPF: A Two‐Stage Merging Planning Framework for Dense Traffic

Chen

Cao

Guo

et al. 2023

Advanced Intelligent Systems

View full text Add to dashboard Cite

Planning for autonomous vehicles to merge into high‐density traffic flows within limited mileage is quite challenging. Specifically, the driving trajectory will inevitably have intersections with other vehicles whose driving intentions can't be directly observed. Herein, a two‐stage algorithm framework that is decomposed into the longitudinal and lateral planning processes for online merging planning is proposed. An improved particle filter is used to estimate the driving models of surrounding vehicles for predicting their future driving intentions. Based on Monte Carlo tree search (MCTS), different action spaces are evaluated for longitudinal merging gap selection and lateral interactive merging operation, while heuristic pruning is used to reduce the computation cost. Moreover, the coefficients related to the driving styles are introduced, and their influences on merging performance are analyzed. Finally, the proposed algorithm is implemented in a two‐lane simulation environment. The results show that the proposal has outperformed other baseline methods.

show abstract

A Belief State Planner for Interactive Merge Maneuvers in Congested Traffic

Cited by 70 publications

References 15 publications

Cooperation-Aware Reinforcement Learning for Merging in Dense Traffic

Cooperation-Aware Reinforcement Learning for Merging in Dense Traffic

A Risk and Comfort Optimizing Motion Planning Scheme for Merging Scenarios

TMPF: A Two‐Stage Merging Planning Framework for Dense Traffic

Contact Info

Product

Resources

About