Autonomous Vehicle Pickup Risk Detection and Mitigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in ensuring passenger safety during pickup and drop-off scenarios, as these situations often involve unusual road conditions and markers that may not provide adequate guidance.
Innovation Solution
The implementation of a passenger safety system that uses sensor and map data to detect unsafe conditions, calculates a safety confidence score, and overrides vehicle operations to mitigate risks by altering trajectories or preventing door openings.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the autonomous vehicle stops at unusual places in the roadway for passenger pickup/delivery, then the passenger service capability is improved, but the safety of passenger pickup and delivery deteriorates
Solution Approach 1:
The system performs preliminary safety assessment by detecting objects in the roadway and calculating safety confidence scores before allowing the vehicle to stop for passenger pickup or delivery. This advance detection and evaluation prevents unsafe stopping scenarios from occurring.
Solution Approach 2:
The safety confidence score acts as an intermediary parameter that mediates between the desire to provide passenger service and the need to ensure safety. The system uses this intermediate metric to make informed decisions about whether to permit stopping at a given location.
2Reliability
If the vehicle uses sensor data to detect unsafe conditions and alter operations, then passenger safety is improved, but the device complexity increases
Solution Approach 1:
The existing sensor system, originally designed for general autonomous vehicle navigation, is repurposed to also detect unsafe conditions for passenger pickup and delivery. This multi-functional use of sensors avoids adding dedicated hardware while enhancing safety capabilities.
Solution Approach 2:
The system uses its own existing sensor data and processing capabilities to perform safety assessments, rather than requiring entirely separate detection systems. The autonomous vehicle leverages its inherent sensing and computation resources to solve the passenger safety problem.
Data Source
AI summary
A passenger may be rather vulnerable to safety risks during pickup and/or drop-off of a passenger by a vehicle. To mitigate or eliminate such risk, the vehicle may determine an endpoint for a vehicle route to pickup or drop-off a passenger at a location. The vehicle may determine an estimated path between the endpoint and the location and may determine a safety confidence score by a machine-learned model for the estimated path and/or may predict a trajectory of a detected object to ascertain whether the estimated path is safe. The vehicle may execute any of a number of different mitigation actions to reduce or eliminate a safety risk if one is detected.