Autonomous Vehicle Collision Avoidance via Independent Safety Processor
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in effectively avoiding collisions due to their complex navigational control systems being overwhelmed by parallel tasks, leading to poor response or lack of response to obstacles in their driving path, which can result in property damage or harm to humans.
Innovation Solution
The implementation of one or more processors independent of the navigational controller to determine the presence of objects in the driving path, allowing for faster and error-free processing of sensor signals, and providing a stop signal to prevent collisions, thereby creating multiple safety mechanisms for safer operation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the navigational controller processes sensor signals to detect obstacles, then the autonomous vehicle can identify objects in its path, but the complex parallel tasks overwhelm the controller and delay response time
Solution Approach 1:
The patent divides the control system into two independent processors: a navigational controller for route planning and a separate safety processor for collision avoidance. This segmentation allows each processor to specialize in specific tasks, with the safety processor dedicating full resources to detecting obstacles and triggering emergency stops, thereby reducing response time without compromising navigation functionality.
Solution Approach 2:
The safety processor acts as an intermediary between the sensor systems and the motor controller. It receives sensor data directly, processes it independently, and can trigger emergency stops without waiting for the navigational controller's decision, thus bridging the gap between detection and action to minimize response time.
2Adaptability or versatility
If the navigational controller handles multiple parallel tasks, then the autonomous vehicle can perform comprehensive functions, but processing resources are depleted and error-prone operation occurs
Solution Approach 1:
The control architecture is segmented into distinct functional modules: navigational controller for high-level planning and a dedicated safety processor for real-time obstacle detection. This segmentation ensures that the safety-critical functions are handled by a specialized processor that does not share resources with other tasks, thereby maintaining high reliability and accuracy in obstacle detection.
Solution Approach 2:
The safety processor creates an independent copy of the obstacle detection and emergency stop functionality, separate from the navigational controller. This redundant safety system operates in parallel and can override the navigational controller if necessary, ensuring that collision avoidance capabilities are preserved even when the main controller is overwhelmed.
3Device complexity
If a single navigational controller is used for both navigation and collision avoidance, then the system structure is simplified, but the controller cannot process safety-critical signals quickly enough
Solution Approach 1:
The control system is segmented into two independent processors: a navigational controller for route planning and a separate safety processor for collision avoidance. This segmentation increases hardware complexity but enables parallel processing, where the safety processor can detect obstacles and trigger emergency stops at maximum speed without being constrained by the navigational controller's processing schedule.
Solution Approach 2:
The safety processor serves as an intermediary that sits between the sensor systems and the motor controller, processing safety-critical signals at high speed and可以直接 triggering emergency stops without waiting for the navigational controller, thus achieving fast response while maintaining a relatively simple overall system architecture.
Data Source
AI summary
Systems for collision avoidance by an autonomous vehicle include a navigational controller adapted to (i) control a driving path of the autonomous vehicle, (ii) process sensor signals from a first sensor system, and (iii) determine whether an object is present in the driving path of the autonomous vehicle based on the sensor signals from the first sensor system. The systems can also include a processor, operationally independent from the navigational controller, adapted to (a) process sensor signals from a second sensor system and (b) determine whether an object is present in the driving path of the autonomous vehicle based on the sensor signals from the second sensor system.