Collision mitigation static occupancy grid
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in safely navigating through environments without colliding with obstacles, as existing technologies lack effective methods to verify trajectories and mitigate collisions in real-time.
Innovation Solution
A collision mitigation system using a static occupancy grid that projects vehicle trajectories and sensor data onto a grid, determining obstacle presence and triggering braking or alerts to avoid collisions by simulating vehicle movement and applying maximum jerk and deceleration when obstacles are detected.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If processed sensor data is used to detect obstacles, then the detection speed is fast, but the detection precision is insufficient leading to missed obstacles
Solution Approach 1:
The patent segments sensor data into two categories: processed sensor data for fast initial obstacle detection and raw sensor data for verification. By dividing the data processing into these two segments, the system achieves both speed (through processed data) and precision (through raw data verification) without requiring a single complex processing pipeline.
Solution Approach 2:
The patent introduces an occupancy grid as an intermediary data structure that stores processed sensor data. This grid serves as a mediator between the fast processed data and the detailed raw sensor data, allowing the system to efficiently compare and verify obstacle detections without directly processing all raw data at full resolution.
2Reliability
If raw sensor data is processed to verify trajectory safety, then the collision detection reliability is improved, but the computational time increases
Solution Approach 1:
The patent performs preliminary processing of sensor data to create the occupancy grid before trajectory verification. This preliminary action organizes sensor data into a structured format that enables rapid verification during trajectory checking, reducing the computational time required when actual verification is needed.
Solution Approach 2:
The patent applies partial processing to raw sensor data by only verifying cells that overlap with the trajectory rather than processing the entire sensor dataset. This selective verification approach maintains high reliability for trajectory safety while significantly reducing computational time by focusing only on relevant areas.
3Measurement precision
If the occupancy grid is updated continuously with new sensor data, then the obstacle detection accuracy is improved, but the processing load increases
Solution Approach 1:
The patent updates the occupancy grid periodically or at specific intervals rather than continuously processing every new sensor data point. This periodic update approach maintains accurate obstacle detection by regularly refreshing the grid while reducing processing energy consumption compared to continuous updates.
Solution Approach 2:
The patent applies different processing quality to different parts of the occupancy grid based on their relevance to the trajectory. Cells that overlap with the trajectory receive more thorough verification using raw sensor data, while other cells use standard processed data updates. This local quality approach improves accuracy where needed while conserving processing energy in less critical areas.
Data Source
AI summary
A system and method for avoiding or mitigating collisions by an autonomous vehicle is provided. Raw sensor data for the vehicle's environment is received, such as through a perception system of the vehicle. A trajectory is also received, the trajectory having a width corresponding to a distance that is at least as wide as the vehicle. The trajectory and raw sensor data are projected onto a grid, such as a static occupancy grid, having a plurality of cells. It is determined whether any cell that overlaps with the trajectory includes the raw sensor data. It is further determined, based on the raw sensor data, whether an obstacle is present along the trajectory. When no obstacles are determined to be present along the trajectory, the trajectory may be verified. However, where obstacles are determined to be present, the vehicle may take an action to avoid collision.