An Autonomous Driving Framework for Long-Term Decision-Making and Short-Term Trajectory Planning on Frenet Space

Moghadam, Majid; Elkaim, Gabriel Hugh

doi:10.1109/case49439.2021.9551559

Cited by 15 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In CARLA, we compare with the framework proposed in [26] (hereafter called frenet ), which firstly samples longitudinal and lateral through the lattices, and then generates a polynomial trajectory by solving the Two‐Point Boundary Value Problems (TPBVPs). In the decision‐making part, we use a simple decision tree to make a lane‐change decision.…”

Section: Methodsmentioning

confidence: 99%

“…The length of the test road is 300 m, which is slightly shorter. [26] builds a motion planner and trajectory generator in the CARLA simulator to implement decision-making and planning, showing the promising performance and the scalability of the framework. The advantage of using data sets or the generated data by driving models is that it can reflect the driving diversity of the human driver, however, it is not easy to demonstrate the interaction between vehicles.…”

Section: Experimental Evaluationmentioning

confidence: 99%

“…To verify our proposed algorithm, we carry out experimental verification in two popular simulation environments, named CARLA and highway-env shown in Figure 1 (Screenshots of CARLA are obtained by work [26]). The reason why we choose the two simulators is that their focus is different, by which the performance of the algorithm can be tested more comprehensively.…”

Section: Configuration Of the Dynamic Environmentmentioning

confidence: 99%

See 2 more Smart Citations

Spatio‐temporal decision‐making and trajectory planning framework with flexible constraints in closed‐loop dynamic traffic

Zhang

Liu

et al. 2022

IET Intelligent Trans Sys

View full text Add to dashboard Cite

Driving in interactive dynamic traffic is a huge challenge for autonomous vehicles, especially for motion planning. The autonomous vehicle not only needs to predict the future states of the social vehicles to avoid a collision but also realizes the comfort and continuous plan. To deal with the problem, a spatio‐temporal decision‐making and motion planning framework with flexible constraints based on previous work is proposed. Improvements can be highlighted in three aspects. First, a neural network for trajectory prediction is trained and it is integrated into the framework, which can learn the social vehicles' reactions in the negotiation better and give more accurate predictions. Second, instead of setting the fixed local targets, the flexible‐constraint mechanism is introduced to increase the success rate of continuous planning, specifically, the local planning target is determined conditioned on the situation with an elastic factor. Third, two popular simulators with randomly disposed traffic participants are exploited, where vehicles are mutually influenced, more similar to real‐world traffic. The closed‐loop tests with zero crashes and the comparative experiments with traditional models demonstrate the superior performance and practical significance of the proposed framework.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Experimental Evaluationmentioning

confidence: 99%

Section: Configuration Of the Dynamic Environmentmentioning

confidence: 99%

See 1 more Smart Citation

Spatio‐temporal decision‐making and trajectory planning framework with flexible constraints in closed‐loop dynamic traffic

Zhang

Liu

et al. 2022

IET Intelligent Trans Sys

View full text Add to dashboard Cite

show abstract

“…However, trajectory generation for configuration spaces with high degrees of freedom is inefficient and easily falls into local minima; therefore, this method is generally suitable for low-dimensional configuration spaces. Discretization methods [18], [25]- [29], such as state lattices, typically cannot meet the demand when driving situations suddenly become more hazardous. In addition, considering the execution efficiency of the computer, the granularity of discretization cannot be too high; otherwise, it may not be possible to discover narrow passages quickly enough to generate feasible motions in a critical situation.…”

Section: Related Workmentioning

confidence: 99%

Motion Planning for Dynamic Scenario Vehicles in Autonomous-Driving Simulations

2023

IEEE Access

View full text Add to dashboard Cite

Scenario vehicles are an important part of the dynamic environment utilized in autonomousdriving simulations. They are required to meet the demands of traffic-scenario diversity and form a larger coverage scale in the road network. However, the current motion planning of scenario vehicles either adheres to the classical microscopic traffic-flow model or follows a predefined path; thus, interacting with the vehicle under test in a dynamic bidirectional fashion is difficult. This study researches a motion-planning method for a broader category of unmanned vehicles and proposes a motion-planning method for scenario vehicles based on Pontryagin's minimal principle, used in optimal control theory and the closed-form solution of the minimum snap method. The study reclassifies actions received from the behavior layer according to the boundary conditions and final times and derives an analytical solution for each of them. The analytical solution is then experimentally verified. The proposed method not only accomplishes efficient motion planning but also exhibits variant driving styles, which provides a practical solution for the motion planning of scenario vehicles in simulations.

show abstract

“…This algorithm can be applied in some lane-changing scenarios with complicated surroundings. Moghadam and Elkaim [23] presented a hierarchical framework for trajectory planning, which generated a set of candidate trajectories known as lattices at each time step. The suitable trajectory is selected through optimization.…”

Section: Literature Reviewmentioning

confidence: 99%

QPNet: Lane‐changing trajectory planning combining quadratic programming and neural network under the convex optimization framework

Wang

Wei

2022

IET Intelligent Trans Sys

View full text Add to dashboard Cite

Lane-changing is a basic driving behaviour, which largely impacts on traffic safety and efficiency. With the development of technology, the automated lane-changing system has attracted extensive attention. Among it, the trajectory planning part is a challenging problem owing to the complexity and diversity of the driving situations. The planner requires the real-time capability to produce safe and comfortable trajectories for coping with the dynamically changing environment. Based on this, the paper proposes a lane-changing trajectory planning model in dynamic driving environments. The model constructs a neural network to predict the end position of the ego vehicle, and then adopts the mathematical programming method to solve the optimal lane-changing trajectory that guarantees the ride safety and comfort. With the assistance of the neural network, the lane-changing trajectory planning problem is converted into a quadratic programming (QP) model, thereby achieving rapid solution of the model. Moreover, to train the proposed algorithm, a novel approach for generating the scenario data is designed, which can generate rich and diverse traffic scenarios at a low cost. The simulation results show that the proposed model can plan a lane-changing trajectory quickly and effectively, and the ego vehicle can follow the planned trajectory safely and comfortably.

show abstract

An Autonomous Driving Framework for Long-Term Decision-Making and Short-Term Trajectory Planning on Frenet Space

Cited by 15 publications

References 15 publications

Spatio‐temporal decision‐making and trajectory planning framework with flexible constraints in closed‐loop dynamic traffic

Spatio‐temporal decision‐making and trajectory planning framework with flexible constraints in closed‐loop dynamic traffic

Motion Planning for Dynamic Scenario Vehicles in Autonomous-Driving Simulations

QPNet: Lane‐changing trajectory planning combining quadratic programming and neural network under the convex optimization framework

Contact Info

Product

Resources

About