Low-Latency Braking System for Autonomous Vehicles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in quickly responding to potential collisions due to the sequential processing requirements of their sensing, perception, prediction, and motion planning systems, which can lead to delayed braking actions.
Innovation Solution
A low-latency braking system that bypasses certain analysis steps, such as object classification and trajectory prediction, to rapidly determine if an object is within the vehicle's path and implement a braking action based on existing sensor data and motion plans, allowing for quicker response times.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the autonomous vehicle uses sequential processing through sensing, perception, prediction, and motion planning systems, then the vehicle can perform comprehensive environmental analysis and generate appropriate motion plans, but the reaction time to potential collisions is delayed
Solution Approach 1:
The patent segments the collision response system into two independent parts: a primary autonomy system for comprehensive environmental analysis and a separate low-latency braking system for rapid collision response. The low-latency braking system receives only essential inputs (sensor data and motion plan) and performs rapid collision detection without executing the full perception and prediction pipeline, thereby reducing reaction time while maintaining safety.
Solution Approach 2:
The patent extracts the critical collision detection function from the sequential processing chain and implements it as a standalone low-latency braking system. This extracted system bypasses non-essential processing steps (detailed perception, prediction, and motion planning) and directly determines whether braking is needed based on simple geometric collision detection, achieving faster response times.
2Loss of time
If the autonomous vehicle implements a low-latency braking system that bypasses certain analysis steps, then the reaction time to potential collisions is reduced, but the complexity of the system architecture increases
Solution Approach 1:
The patent merges the low-latency braking system with the existing autonomy system by having them share common inputs (sensor data and motion plan) and coordinate their outputs. The low-latency braking system operates in parallel with the primary autonomy system, and both systems can independently command the vehicle to brake. This merging approach adds functionality without requiring completely separate sensing or control hardware, thereby limiting the increase in overall system complexity.
3Reliability
If the autonomous vehicle performs comprehensive perception, prediction, and motion planning before braking, then the braking action is well-informed and accurate, but the computational processing time increases
Solution Approach 1:
The low-latency braking system performs only the minimal necessary action for collision response: it checks whether any detected object intersects with the vehicle's planned path and triggers braking if needed. It deliberately omits comprehensive object classification, detailed trajectory prediction, and complex motion planning, performing only the partial action needed for rapid collision avoidance while the primary autonomy system continues its more thorough analysis.
Data Source
AI summary
Systems and methods for implementing a low-latency braking action for an autonomous vehicle are provided. A computing system can include a vehicle autonomy system comprising one or more processors configured to determine a motion plan for an autonomous vehicle based at least in part on sensor data from one or more sensors of the autonomous vehicle. The computing system can further include a low-latency braking system comprising one or more processors configured to determine that the autonomous vehicle has a likelihood of colliding with an object in a surrounding environment based at least in part on a previously-determined motion plan obtained from the vehicle autonomy system. In response to determining that the autonomous vehicle has a likelihood of colliding with the object in the surrounding environment, the low-latency braking system can further be configured to implement a braking action for the autonomous vehicle.