Autonomous Vehicle Stoppage Severity Levels for Motion Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in safely and efficiently changing their path to avoid obstacles and stop in a safe manner, especially in dynamic and unpredictable environments, requiring improved methods to determine the severity of stoppage conditions and generate optimal motion plans.
Innovation Solution
A computer-implemented method and system that receives state data from an autonomous vehicle and its environment, determines vehicle stoppage conditions, selects a severity level from a plurality of levels, and generates a motion plan that complies with associated constraints, including location, time, and trajectory changes, using machine-learned models and sensors to optimize stopping locations and trajectories.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the autonomous vehicle rapidly changes its path to avoid obstacles, then vehicle safety is improved, but the complexity of motion planning increases
Solution Approach 1:
The motion planning problem is segmented into multiple discrete severity levels (e.g., Level 1: normal operation, Level 2: cautious operation, Level 3: emergency stop). Each severity level has predefined constraints and decision rules, breaking down the complex continuous decision space into manageable discrete categories that simplify real-time processing while maintaining safety responses.
Solution Approach 2:
The system changes operational parameters based on detected severity levels. When a stoppage condition is detected, the system adjusts key parameters such as maximum speed, acceleration limits, and stopping distance according to the predefined constraints of the corresponding severity level. This parameter adaptation allows rapid response to safety concerns without requiring complex real-time optimization.
2Manufacturing precision
If the autonomous vehicle implements multiple severity levels with different constraints, then stopping precision is improved, but the computational complexity increases
Solution Approach 1:
The constraints for each severity level are predetermined and stored in the system before operation. When a stoppage condition occurs, the system simply retrieves and applies the pre-defined constraints corresponding to the detected severity level, rather than computing optimal constraints in real-time. This preliminary preparation of constraint sets enables precise stopping behavior without heavy computational burden during critical moments.
3Reliability
If the autonomous vehicle stops immediately upon detecting stoppage conditions, then safety is improved, but traffic flow disruption increases
Solution Approach 1:
The system dynamically adjusts the stopping behavior based on the detected severity level. For minor stoppage conditions, the vehicle applies gentle deceleration and may continue moving at reduced speed. For severe conditions, immediate hard stopping is enacted. This dynamic response strategy balances safety requirements with traffic flow considerations, preventing unnecessary disruptions for non-critical situations while ensuring rapid stops when truly needed.
Data Source
AI summary
Systems, methods, tangible non-transitory computer-readable media, and devices for operating an autonomous vehicle are provided. For example, the disclosed technology can include receiving state data that includes information associated with states of an autonomous vehicle and an environment external to the autonomous vehicle. Responsive to the state data satisfying vehicle stoppage criteria, vehicle stoppage conditions can be determined to have occurred. A severity level of the vehicle stoppage conditions can be selected from a plurality of available severity levels respectively associated with a plurality of different sets of constraints. A motion plan can be generated based on the state data. The motion plan can include information associated with locations for the autonomous vehicle to traverse at time intervals corresponding to the locations. Further, the locations can include a current location of the autonomous vehicle and a destination location at which the autonomous vehicle stops traveling.