Autonomous Vehicle Speed Profile via Pre-computed Risk Scenarios
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in accurately determining environmental risks and generating effective motion plans to ensure safe operation, particularly in dynamic environments with unpredictable objects.
Innovation Solution
A computer-implemented method that accesses vehicle and perception data to determine scenario exposure, predicts object trajectories, and generates a speed profile based on hypothetical vehicle speeds and distances, ensuring the autonomous vehicle operates within predefined safety thresholds.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the autonomous vehicle uses complex risk assessment and multiple hypothetical scenarios to determine safe speeds, then the safety and reliability of vehicle operation is improved, but the computational complexity and processing time increase
Solution Approach 1:
The system pre-calculates and stores speed profiles for various hypothetical scenarios before actual operation. When an object is detected, the system retrieves and applies pre-determined speed profiles rather than computing everything in real-time, reducing computational complexity while maintaining safety
Solution Approach 2:
The risk assessment is divided into discrete hypothetical scenarios (different object behaviors, different speeds, different distances). Each scenario is evaluated separately using the same computational framework, allowing the system to manage complexity through modular scenario-based analysis
2Reliability
If the autonomous vehicle calculates multiple hypothetical speeds and distances to ensure safety, then the reliability of collision avoidance is improved, but the time required for decision-making increases
Solution Approach 1:
Speed profiles are pre-computed for various hypothetical scenarios and stored for quick retrieval. During operation, the system selects and applies appropriate pre-computed profiles based on current conditions, significantly reducing real-time computation time while maintaining thorough safety analysis
Solution Approach 2:
The system varies key parameters (speed, distance, object behavior) across multiple hypothetical scenarios to ensure comprehensive safety assessment. By systematically changing these parameters in pre-computed scenarios, the system achieves thorough collision avoidance analysis without excessive real-time processing
3Reliability
If the autonomous vehicle maintains lower speeds to reduce risk exposure in dynamic environments, then the safety of operation is improved, but the productivity and efficiency of transportation decrease
Solution Approach 1:
The speed profile is dynamically adjusted based on the specific scenario and object behavior. Rather than maintaining a fixed low speed, the system determines the maximum safe speed for each situation using pre-computed profiles, allowing the vehicle to travel as fast as safety conditions permit
Solution Approach 2:
The system changes the speed parameter based on scenario exposure and object predictions. By systematically evaluating different speed parameters in pre-computed scenarios, the system identifies the optimal speed that maximizes both safety and efficiency for each specific situation
Data Source
AI summary
Systems, methods, tangible non-transitory computer-readable media, and devices associated with vehicle control based on risk-based interactions are provided. For example, vehicle data and perception data can be accessed. The vehicle data can include the speed of an autonomous vehicle in an environment. The perception data can include location information and classification information associated with an object in the environment. A scenario exposure can be determined based on the vehicle data and perception data. Prediction data including predicted trajectories of the object can be accessed. Expected speed data can be determined based on hypothetical speeds and hypothetical distances between the vehicle and the object. A speed profile that satisfies a threshold criteria can be determining based on the scenario exposure, the prediction data, and the expected speed data, over a distance. A motion plan to control the autonomous vehicle can be generated based on the speed profile.