Collision Alert System for Autonomous Vehicle Takeover
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles operating in manual mode may reduce the probability of collision, but require a human driver to be constantly attentive to take over control, which is a demanding requirement due to the limitations of the driving-by-wire system's deceleration and steering capabilities compared to a human driver.
Innovation Solution
A system that generates an alert message for a human driver to take over the vehicle by comparing collision times and relative speeds between autonomous and manual driving trajectories, using control values for deceleration and wheel steering, and sending the alert via a CAN bus or horn alarm to facilitate timely intervention.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the driving-by-wire system operates in autonomous mode with limited deceleration (0.2G), then the possibility of extreme movements is minimized, but the ability to reduce collision probability is limited
Solution Approach 1:
The system performs preliminary action by continuously monitoring the driving environment and calculating alternative trajectories in advance. When a collision risk is detected, the system has already prepared the alert message and trajectory comparison results, enabling the safety operator to take over control immediately without delay, thus resolving the contradiction between limited autonomous deceleration capability and collision avoidance effectiveness.
2Productivity
If a human driver sits in the ADV to take over control when danger is detected, then collision probability can be reduced, but the driver must be constantly attentive which is a demanding requirement
Solution Approach 1:
The system implements feedback by continuously monitoring the driving environment, calculating collision risks, and providing alert messages to the safety operator only when necessary. The system compares autonomous trajectory with manual driving trajectory and provides feedback about collision probability differences, allowing the operator to remain passive during normal operation and only become active when the system indicates a potential collision scenario.
Solution Approach 2:
The system performs self-service by autonomously monitoring the driving environment, calculating trajectories, and determining when human intervention is needed. The system independently handles the complex task of continuous environmental assessment and trajectory optimization, freeing the safety operator from the burden of constant attentiveness while maintaining the ability to intervene when necessary.
3Productivity
If the driving-by-wire system uses maximal control values for deceleration, then collision probability may be reduced, but the system may make extreme movements which increases safety risks
Solution Approach 1:
The system applies partial action by using limited deceleration (0.2G) under normal autonomous operation, which is sufficient for most scenarios. However, when a collision risk is detected and the safety operator takes over, the system can apply excessive action with full human-capable deceleration (0.6G). This resolves the contradiction by matching the deceleration level to the situation severity.
Solution Approach 2:
The system implements dynamics by making the deceleration capability adjustable based on operational mode. In autonomous mode, the system uses limited deceleration (0.2G) to prevent extreme movements. When manual takeover is triggered, the system dynamically switches to allow full human-capable deceleration (0.6G), enabling the vehicle to respond appropriately to the severity of the situation while maintaining safety under normal conditions.
Data Source
AI summary
In one embodiment, a first trajectory is generated for a driving environment using control values allowed for a driving-by-wire system. If the trajectory includes a collision with an object, the ADV estimates the time of the collision and the relative speed between the ADV and the object at the time of the collision. A second trajectory is then generated for the driving environment using control values allowed for a human driver. The time of the collision and the relative speed between the ADV and the object at the time collision on the second trajectory are also estimated. The ADV then compares the two collision times and the two relative speeds, and based on the comparison, generates an alert message for the human driver to take over the control of the ADV.