Adaptive Potential Field-Based Path Planning for Complex Autonomous Driving Scenarios

Lu, Bing; Li, Guofa; Yu, Huilong; Wang, Hong; Guo, Jinquan; Cao, Dongpu; He, Haibo

doi:10.1109/access.2020.3044909

Cited by 45 publications

(16 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To verify the performance of the proposed SPMPC, we conducted a comparative simulation study with the latest PF-AMPC [19] using MATLAB/Simulink and CarSim in two emergency collision avoidance scenarios: i) Two-lane traffic at same direction and ii) Three-lane traffic at same direction. The parameter settings of the potential field are described in Table I, which is discussed in [11], [17].…”

Section: Simulation Resultsmentioning

confidence: 99%

“…later, [15], [16] combines the clothoidal curve with the PFs to consider vehicle dynamics and real world traffic data for emergency collision avoidance in the process of path generation, but only single driving scenario is simulated in the comparative study. For considering multiple obstacle vehicles on the highway, [19] proposes an adaptive PFs-based model predictive controller by overlapping two Gaussian probability density functions to compute the 3D risk field more accurately, but only straight-ahead obstacle vehicles that maintain a long Euclidean distance were considered in this study. In general, prior studies have one common limitation: emergency avoidance due to unexpected deceleration of the obstacle vehicle has not been considered.…”

mentioning

confidence: 99%

“…1. The proposed PF-SPMPC method was simulated in a comparative emergency scenario, wherein it was compared with the latest adaptive PF-based MPC (PF-AMPC) approach [19] under co-simulation in MAT-LAB/Simulink and CarSim. The results show that the proposed method outperforms the latest approach in eliminating severe oscillations when passing through a narrow passage.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Model Predictive Path-Planning Controller With Potential Function for Emergency Collision Avoidance on Highway Driving

Lin

Tsukada

2022

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Existing potential functions (PFs) utilized in autonomous vehicles mainly focus on solving the path-planning problems in some conventional driving scenarios; thus, their performance may not be satisfactory in the context of emergency obstacle avoidance. Therefore, we propose a novel model predictive path-planning controller (MPPC) combined with PFs to handle complex traffic scenarios (e.g., emergency avoidance when a sudden accident occurs). Specifically, to enhance the safety of the PFs, we developed an MPPC to handle an emergency case with a sigmoid-based safe passage embedded in the MPC constraints (SPMPC) with a specific triggering analysis algorithm on monitoring traffic emergencies. The presented PF-SPMPC algorithm was compiled in a comparative simulation study using MATLAB/Simulink and CarSim. The algorithm outperformed the latest PF-MPC approach to eliminate the severe tire oscillations and guarantee autonomous driving safety when handling the traffic emergency avoidance scenario.

show abstract

Section: Simulation Resultsmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Model Predictive Path-Planning Controller With Potential Function for Emergency Collision Avoidance on Highway Driving

Lin

Tsukada

2022

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

show abstract

“…Recent studies proposed the application of potential fields to path planning optimization [12] with fuzzy logic [13] or with a Kalman-filter-like observer [14]. An adaptive potential field was recently developed for autonomous vehicles in complex driving scenarios such as emergency braking and accelerating [15]. Again, most of the above were limited to numerical simulation without any tracking/speed control and computation loading concerns.…”

Section: Introductionmentioning

confidence: 99%

Development of an Improved Rapidly Exploring Random Trees Algorithm for Static Obstacle Avoidance in Autonomous Vehicles

Yang

Lin

2021

Sensors

View full text Add to dashboard Cite

Safe path planning for obstacle avoidance in autonomous vehicles has been developed. Based on the Rapidly Exploring Random Trees (RRT) algorithm, an improved algorithm integrating path pruning, smoothing, and optimization with geometric collision detection is shown to improve planning efficiency. Path pruning, a prerequisite to path smoothing, is performed to remove the redundant points generated by the random trees for a new path, without colliding with the obstacles. Path smoothing is performed to modify the path so that it becomes continuously differentiable with curvature implementable by the vehicle. Optimization is performed to select a “near”-optimal path of the shortest distance among the feasible paths for motion efficiency. In the experimental verification, both a pure pursuit steering controller and a proportional–integral speed controller are applied to keep an autonomous vehicle tracking the planned path predicted by the improved RRT algorithm. It is shown that the vehicle can successfully track the path efficiently and reach the destination safely, with an average tracking control deviation of 5.2% of the vehicle width. The path planning is also applied to lane changes, and the average deviation from the lane during and after lane changes remains within 8.3% of the vehicle width.

show abstract

“…The idea is to generate a spatial safety corridor based on the surrounding occupancies, and use the corridor as a constraint in trajectory planning. The trajectories are then generated in SLT (Frenet) frame [1] or XY T (Cartesian) frame [2], aiming to optimize the overall swiftness, smoothness, and smartness [3], under the constraints of continuity, vehicle dynamics limitation, traffic rules, and above all, safety [4].…”

Section: Introductionmentioning

confidence: 99%

A Sufficient Condition for Convex Hull Property in General Convex Spatio-Temporal Corridors

Zhang¹,

Yadmellat²

2021

Preprint

View full text Add to dashboard Cite

Motion planning is one of the key modules in autonomous driving systems to generate trajectories for selfdriving vehicles to follow. A common motion planning approach is to generate trajectories within semantic safe corridors. The trajectories are generated by optimizing parametric curves (e.g. Bezier curves) according to an objective function. To guarantee safety, the curves are required to satisfy the convex hull property, and be contained within the safety corridors. The convex hull property however does not necessary hold for timedependent corridors, and depends on the shape of corridors. The existing approaches only support simple shape corridors, which is restrictive in real-world, complex scenarios. In this paper, we provide a sufficient condition for general convex, spatio-temporal corridors with theoretical proof of guaranteed convex hull property. The theorem allows for using more complicated shapes to generate spatio-temporal corridors and minimizing the uncovered search space to O( 1 n 2 ) compared to O(1) of trapezoidal corridors, which can improve the optimality of the solution. Simulation results show that using general convex corridors yields less harsh brakes, hence improving the overall smoothness of the resulting trajectories.

show abstract

Adaptive Potential Field-Based Path Planning for Complex Autonomous Driving Scenarios

Cited by 45 publications

References 35 publications

Model Predictive Path-Planning Controller With Potential Function for Emergency Collision Avoidance on Highway Driving

Model Predictive Path-Planning Controller With Potential Function for Emergency Collision Avoidance on Highway Driving

Development of an Improved Rapidly Exploring Random Trees Algorithm for Static Obstacle Avoidance in Autonomous Vehicles

A Sufficient Condition for Convex Hull Property in General Convex Spatio-Temporal Corridors

Contact Info

Product

Resources

About