Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

eRSS-RAMP: A Rule-Adherence Motion Planner Based on Extended Responsibility-Sensitive Safety for Autonomous Driving

Pengfei Lin, Ehsan Javanmardi, Yuze Jiang, Dou Hu, Shangkai Zhang, Manabu Tsukada

TL;DR

This work proposes a rule-adherence motion planner (RAMP) based on the extended RSS (eRSS) regulation for non-connected and connected AVs in merging and emergency-avoiding scenarios and results indicate that the proposed method can achieve faster and safer lane merging performance.

Abstract

Driving safety and responsibility determination are indispensable pieces of the puzzle for autonomous driving. They are also deeply related to the allocation of right-of-way and the determination of accident liability. Therefore, Intel/Mobileye designed the responsibility-sensitive safety (RSS) framework to further enhance the safety regulation of autonomous driving, which mathematically defines rules for autonomous vehicles (AVs) behaviors in various traffic scenarios. However, the RSS framework's rules are relatively rudimentary in certain scenarios characterized by interaction uncertainty, especially those requiring collaborative driving during emergency collision avoidance. Besides, the integration of the RSS framework with motion planning is rarely discussed in current studies. Therefore, we proposed a rule-adherence motion planner (RAMP) based on the extended RSS (eRSS) regulation for non-connected and connected AVs in merging and emergency-avoiding scenarios. The simulation results indicate that the proposed method can achieve faster and safer lane merging performance (53.0% shorter merging length and a 73.5% decrease in merging time), and allows for more stable steering maneuvers in emergency collision avoidance, resulting in smoother paths for ego vehicle and surrounding vehicles.

eRSS-RAMP: A Rule-Adherence Motion Planner Based on Extended Responsibility-Sensitive Safety for Autonomous Driving

TL;DR

This work proposes a rule-adherence motion planner (RAMP) based on the extended RSS (eRSS) regulation for non-connected and connected AVs in merging and emergency-avoiding scenarios and results indicate that the proposed method can achieve faster and safer lane merging performance.

Abstract

Driving safety and responsibility determination are indispensable pieces of the puzzle for autonomous driving. They are also deeply related to the allocation of right-of-way and the determination of accident liability. Therefore, Intel/Mobileye designed the responsibility-sensitive safety (RSS) framework to further enhance the safety regulation of autonomous driving, which mathematically defines rules for autonomous vehicles (AVs) behaviors in various traffic scenarios. However, the RSS framework's rules are relatively rudimentary in certain scenarios characterized by interaction uncertainty, especially those requiring collaborative driving during emergency collision avoidance. Besides, the integration of the RSS framework with motion planning is rarely discussed in current studies. Therefore, we proposed a rule-adherence motion planner (RAMP) based on the extended RSS (eRSS) regulation for non-connected and connected AVs in merging and emergency-avoiding scenarios. The simulation results indicate that the proposed method can achieve faster and safer lane merging performance (53.0% shorter merging length and a 73.5% decrease in merging time), and allows for more stable steering maneuvers in emergency collision avoidance, resulting in smoother paths for ego vehicle and surrounding vehicles.
Paper Structure (13 sections, 2 theorems, 10 equations, 19 figures, 1 table)

This paper contains 13 sections, 2 theorems, 10 equations, 19 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Potential Field for Collision Avoidance
  4. Potential field
  5. Safe-critical Sigmoid Generator
  6. Rule-Adherence Motion Planner with Extended Responsibility-Sensitive Safety
  7. Lane Merging on the Highway
  8. Collision Avoidance with Static Objects on the Highway
  9. Collision Avoidance with Dynamic Objects on the Highway
  10. Simulation Results and Analysis
  11. Lane-merge Scenarios
  12. Emergency Collision Avoidance Scenarios
  13. Conclusion and Discussion

Key Result

Lemma 1

Let $c_e$ be the ego vehicle that is behind the front $j^{th}$ obstacle vehicle $c_f^j$ on the X-axis. Let $v_e$, $v_f^j$ be the longitudinal velocities of the vehicles. Then, the minimum safe distance for the X-axis between $c_e$ and $c_f^j$ is: where $[\textit{h}]_+:\max\{\textit{h},0\}$

Figures (19)

  • Figure 1: Overall system framework of the proposed eRSS-RAMP method: Communication components like the antenna and transmitter enable vehicle-to-vehicle interaction. Sensing & Perception gather data from various sensors and process it for environment modeling and localization. Planning includes the extended responsibility-sensitive safety and safe-critical sigmoid generator to manage reference signals (paths, velocity, etc.), while the control module oversees lateral and longitudinal control, directing the actuators (brake, throttle, steering wheel).
  • Figure 2: Sigmoid-based trajectory with the PFs (solid red line) and only PFs-based trajectory (solid green line).
  • Figure 3: Slope at centrosymmetric point of the sigmoid curve.
  • Figure 4: Merging Scenarios with different conditions of the traffic
  • Figure 5: Collision avoidance in the static environment and emergency scenarios
  • ...and 14 more figures

Theorems & Definitions (7)

  • Lemma 1: Safe Longitudinal Distance
  • Lemma 2: Safe Lateral Distance
  • Definition 1: Merging in Non-cooperative Driving
  • Definition 2: Merging in Cooperative Driving
  • Definition 3: Collision Avoidance with Static Objects
  • Definition 4: Emergency Avoidance in Non-cooperative Driving
  • Definition 5: Emergency Avoidance in Cooperative Driving