Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Efficient and Safe Planner for Automated Driving on Ramps Considering Unsatisfication

Qinghao Li, Zhen Tian, Xiaodan Wang, Jinming Yang, Zhihao Lin

TL;DR

The paper tackles the challenge of safe and efficient AV lane changes on ramps by introducing an integrated planner that couples an unsatisfactory level–based decision mechanism with arrow-cluster–based trajectory planning. It formulates a two-part framework: (1) decision making using instantaneous and accumulated discomfort to trigger lane changes, and (2) trajectory planning using two quintic polynomial families evaluated by a hybrid loss that accounts for path smoothness, velocity adherence, and collision risk. The approach employs explicit sampling curves and a risk-based loss (U_total) to select safe, comfortable, and efficient lane-change curves, validated through ramp-scenario simulations with promising results such as TTC consistently exceeding 3 s and mean speeds surpassing APF baselines. The work demonstrates improved responsiveness and safety in ramp merging, with potential applicability to more complex ramp geometries and mixed traffic, while outlining future work on computational efficiency and generalization.

Abstract

Automated driving on ramps presents significant challenges due to the need to balance both safety and efficiency during lane changes. This paper proposes an integrated planner for automated vehicles (AVs) on ramps, utilizing an unsatisfactory level metric for efficiency and arrow-cluster-based sampling for safety. The planner identifies optimal times for the AV to change lanes, taking into account the vehicle's velocity as a key factor in efficiency. Additionally, the integrated planner employs arrow-cluster-based sampling to evaluate collision risks and select an optimal lane-changing curve. Extensive simulations were conducted in a ramp scenario to verify the planner's efficient and safe performance. The results demonstrate that the proposed planner can effectively select an appropriate lane-changing time point and a safe lane-changing curve for AVs, without incurring any collisions during the maneuver.

Efficient and Safe Planner for Automated Driving on Ramps Considering Unsatisfication

TL;DR

The paper tackles the challenge of safe and efficient AV lane changes on ramps by introducing an integrated planner that couples an unsatisfactory level–based decision mechanism with arrow-cluster–based trajectory planning. It formulates a two-part framework: (1) decision making using instantaneous and accumulated discomfort to trigger lane changes, and (2) trajectory planning using two quintic polynomial families evaluated by a hybrid loss that accounts for path smoothness, velocity adherence, and collision risk. The approach employs explicit sampling curves and a risk-based loss (U_total) to select safe, comfortable, and efficient lane-change curves, validated through ramp-scenario simulations with promising results such as TTC consistently exceeding 3 s and mean speeds surpassing APF baselines. The work demonstrates improved responsiveness and safety in ramp merging, with potential applicability to more complex ramp geometries and mixed traffic, while outlining future work on computational efficiency and generalization.

Abstract

Automated driving on ramps presents significant challenges due to the need to balance both safety and efficiency during lane changes. This paper proposes an integrated planner for automated vehicles (AVs) on ramps, utilizing an unsatisfactory level metric for efficiency and arrow-cluster-based sampling for safety. The planner identifies optimal times for the AV to change lanes, taking into account the vehicle's velocity as a key factor in efficiency. Additionally, the integrated planner employs arrow-cluster-based sampling to evaluate collision risks and select an optimal lane-changing curve. Extensive simulations were conducted in a ramp scenario to verify the planner's efficient and safe performance. The results demonstrate that the proposed planner can effectively select an appropriate lane-changing time point and a safe lane-changing curve for AVs, without incurring any collisions during the maneuver.

Paper Structure

This paper contains 14 sections, 25 equations, 8 figures.

Table of Contents

  1. Introduction
  2. Related Works
  3. Driving Challenges in Ramp
  4. collision-avoidance with HDVs
  5. Problem Statement
  6. The framework of proposed proposed planner
  7. Vehicle model
  8. Unsatisfactory-based Decision Making
  9. Unsatisfactory Level Calculation
  10. Accumulated Unsatisfactory Level
  11. Double dimensional Sampling Curves
  12. Loss Function for Candidates paths
  13. Simulation Results
  14. conclusion

Figures (8)

  • Figure 1: The proposed integrated unsatisfactory-based decision making and trajectory planning framework.
  • Figure 2: The driving performance in the simulated ramp.
  • Figure 3: The loss curves of $U_{x-y}$,$U_{x-t}$, $U_\text{risk}$, and $U_\text{total}$.
  • Figure 4: Comparison of lane-changing trajectories and corresponding curvature profiles for different methods
  • Figure 5: Comparison of average curvature values for different trajectory generation methods.
  • ...and 3 more figures