Autonomous Vehicle Pedestrian Interaction via Dynamic Feasible Area Velocity Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous driving vehicles face challenges in interacting safely with pedestrians in low-speed scenarios, such as campus environments, where existing interaction strategies are not suitable, and there is a need for effective velocity control to ensure safe navigation.
Innovation Solution
A computer-implemented method for autonomous driving vehicles that receives images from image capturing devices to identify obstacles, generates a feasible area around moving pedestrians, determines an upper bound velocity limit, and generates a trajectory with a velocity less than this limit to control the vehicle's deceleration, ensuring safe distance and speed adjustments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If existing interaction strategies for autonomous driving vehicles on urban roads are used, then the vehicle can navigate autonomously, but the interaction is not suitable for low speed scenarios such as campus environments where pedestrian interaction is more frequent
Solution Approach 1:
The system dynamically adjusts the feasible area parameters and velocity limits based on the detected obstacle type and scene characteristics. For low-speed scenarios with pedestrians, the feasible area is expanded and velocity limits are reduced, while urban road scenarios use different parameters. This dynamic adaptation resolves the contradiction by making the system both versatile across scenarios and reliable within each specific scenario through context-appropriate parameters.
2Productivity
If the autonomous driving vehicle operates at higher speeds, then productivity is improved, but the risk of collision with pedestrians increases in low speed scenarios
Solution Approach 1:
The system changes the velocity parameter dynamically based on the feasible area calculation. When a pedestrian is detected and the vehicle is within the feasible area, an upper bound velocity limit is determined and applied. This parameter change resolves the contradiction by allowing high speed operation when safe (low collision risk) while automatically reducing speed when pedestrians are present (high collision risk), thus maintaining productivity where possible while eliminating harmful effects when necessary.
3Reliability
If the vehicle decelerates when within the feasible area of a moving obstacle, then safety is improved, but the trajectory control complexity increases
Solution Approach 1:
The system performs preliminary calculation of the feasible area and velocity limits before the vehicle enters the deceleration zone. The upper bound velocity limit is determined in advance based on the feasible area boundaries, allowing the trajectory controller to smoothly apply deceleration without last-minute complex calculations. This preliminary action resolves the contradiction by maintaining simple real-time control while ensuring safe deceleration behavior.
Data Source
AI summary
In one embodiment, a system receives a captured image perceiving an environment of an ADV from an image capturing device of the ADV, where the captured image identifies an obstacle in motion near the ADV. The system generates a feasible area surrounding the moving obstacle based on a projection of the moving obstacle. If the ADV is within the feasible area, the system determines an upper bound velocity limit for the ADV. The system generates a trajectory having a trajectory velocity less than the upper bound velocity limit to control the ADV autonomously according to the trajectory such that if the ADV is within the feasible area the ADV is to decelerate.