Rear-Zone VRU Detection for Vehicle Collision Avoidance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Vulnerable road users, such as pedestrians, cyclists, and motorcyclists, are at high risk of rear-end collisions due to limited visibility and protection, which existing technologies fail to adequately address, particularly in city traffic scenarios.
Innovation Solution
A method for autonomous vehicles to detect vulnerable road users behind their rear-ends, providing control instructions to adjust routes, decelerate, or change lanes to prevent collisions, using data on user position, vulnerability, and traffic conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the vehicle maintains its current trajectory and speed, then the vehicle's productivity and efficiency are maintained, but the risk of rear-end collision with vulnerable road users increases
Solution Approach 1:
The system performs preliminary detection of vulnerable road users in the rear zone using sensors before the collision risk materializes. By identifying cyclists, pedestrians, or motorcyclists early and predicting their trajectories, the system can proactively adjust vehicle maneuvers to prevent collisions while maintaining efficient travel.
Solution Approach 2:
The control system acts as an intermediary between the vehicle's driving objectives and the vulnerable road users. It processes sensor data, predicts potential collision scenarios, and generates control instructions that mediate between maintaining productivity and avoiding harm to road users.
2Reliability
If the vehicle implements comprehensive rear-zone monitoring and control adjustments, then the safety of vulnerable road users is improved, but the device complexity increases
Solution Approach 1:
The system uses a multi-functional sensor array that serves both primary driving functions and specialized rear-zone monitoring for vulnerable road users. The same sensors detect obstacles, measure distances, and provide data for collision prediction, eliminating the need for separate dedicated hardware and reducing overall system complexity.
Solution Approach 2:
The control system automatically processes sensor data, identifies vulnerable road users, predicts collision risks, and generates control instructions without requiring external intervention. The system self-manages the entire safety monitoring and intervention process, reducing the need for additional control hardware.
3Reliability
If the vehicle frequently adjusts its trajectory to avoid vulnerable road users, then the safety of vulnerable road users is improved, but the loss of time for the vehicle increases
Solution Approach 1:
The system applies control adjustments only when and where necessary to avoid collisions with vulnerable road users. By selectively intervening based on detected risk levels and predicted trajectories, the system makes partial adjustments rather than continuous trajectory changes, minimizing time loss while maintaining safety.
Solution Approach 2:
When vulnerable road users are detected in low-risk zones or moving away from the vehicle's path, the system skips unnecessary control interventions and maintains the original trajectory. This allows the vehicle to rush through safe zones without deceleration or maneuvering, preserving travel time while remaining ready to intervene when needed.
Data Source
Figure 1
Figure 2~4
Figure 5a~5b
AI summary
The disclosure relates to a computer-implemented method (100) for reducing a risk of a collision of a road user (2) with a rear-end (11) of a vehicle (1). The method (100) comprises obtaining first data indicative of a position of the road user (2) in a zone (3) behind the rear-end (11) of the vehicle (101), obtaining second data indicative of the road user (2) being a vulnerable road user (2) (102), and providing a control instruction for controlling the vehicle (1) for reducing the risk of the rear-end collision based on the first data and the second data (103).