Autonomous Vehicle Speed Planning for Precautionary Slowdown
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional speed planning for autonomous driving vehicles does not adequately consider complex driving environments, leading to insufficient safety precautions in situations like heavy traffic or obstacles, which can compromise safety.
Innovation Solution
A precautionary slowdown predictive model using a deep neural network is integrated into the autonomous driving system, which analyzes sensor data and internal vehicle states to determine if a precautionary slowdown is necessary, and adjusts the speed limit accordingly, thereby enhancing safety in complex environments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional speed planning follows the speed limit without considering driving environment, then the vehicle can maintain high speed and productivity, but safety is compromised in complicated driving environments
Solution Approach 1:
The speed limit is made dynamic rather than fixed. The system continuously adjusts the speed limit based on real-time driving environment assessment. When the environment is assessed as safe, the vehicle can travel at or near the posted speed limit. When complications are detected, the speed limit is automatically reduced. This dynamic adjustment resolves the contradiction by allowing high speed when safe while enabling speed reduction when reliability is prioritized.
Solution Approach 2:
The system changes the parameter of speed limit from a constant value to a variable value that depends on environmental conditions. By introducing environmental factors as variables that modify the speed parameter, the system can optimize both safety and productivity - maintaining high speeds in safe conditions while reducing speeds when safety concerns arise, thus resolving the contradiction between these two opposing requirements.
2Reliability
If the speed limit is reduced in complicated driving environments, then safety is improved, but travel time increases
Solution Approach 1:
The speed limit adjustment is dynamic and condition-based rather than universally applied. The system only reduces speed when the driving environment is assessed as complicated or unsafe. In normal, safe driving conditions, the vehicle maintains the posted speed limit, thus avoiding unnecessary time loss. This dynamic approach resolves the contradiction by minimizing speed reductions to only when safety requires them.
Solution Approach 2:
The system performs preliminary assessment of the driving environment before adjusting speed. By evaluating environmental factors in advance and predicting potential safety issues, the system can proactively adjust speed to prevent safety incidents while avoiding unnecessary slowdowns. This preliminary action allows the system to maintain optimal speed most of the time while only reducing speed when actually needed for safety.
Data Source
AI summary
A driving environment is perceived based on sensor data obtained from a plurality of sensors mounted on an ADV. A first set of features is extracted from the sensor data representing the driving environment, where the first set of features include one or more obstacles moving relative to the ADV. A precaution notification is generated by applying a precautionary slowdown predictive model to the first set of features and a second set of features determined based on internal states of the ADV. In response to the precaution notification, a speed planning is performed to lower a speed limit of the ADV to a predetermined percentage of the speed limit. The ADV is controlled to drive autonomously according to the lowered speed limit to perform a precautionary slowdown.