Autonomous Vehicle Junction State Machine Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in safely navigating through environments with traffic controls like red lights, particularly when encountering multiple vehicles or occlusions, which can hinder their ability to execute right turns on red legally and safely.
Innovation Solution
A state machine approach with states such as approach, prepare to stop, stop, proceed with caution, and go, utilizing sensor data from lidar, radar, and image data to determine transition speeds and caution regions, allowing the vehicle to adapt to real-time visibility and occlusions for safe maneuvering.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the autonomous vehicle uses traditional control methods at junctions, then the vehicle can follow simple traffic rules, but the vehicle cannot safely handle complex scenarios with multiple vehicles and occlusions
Solution Approach 1:
The control system is divided into discrete states (approach, prepare to stop, stop, proceed with caution, go) that segment the complex decision-making process into manageable transitions. Each state has specific entry and exit conditions, allowing the system to handle complex junction scenarios through a structured state machine rather than a monolithic control algorithm.
Solution Approach 2:
The state machine allows dynamic transitions between states based on real-time sensor data and environmental conditions. The vehicle can adapt its behavior dynamically by transitioning between states (e.g., from stop to proceed with caution when the junction is clear), enabling safe handling of complex scenarios while maintaining a relatively simple underlying control structure.
2Reliability
If the autonomous vehicle collects and processes extensive sensor data for junction traversal, then the vehicle can improve safety and collision avoidance, but the processing resources are consumed
Solution Approach 1:
The system processes sensor data selectively based on the current state and specific needs of junction traversal. Rather than continuously processing all sensor data at full capacity, the system activates processing only when relevant to current state transitions (e.g., evaluating sensor data specifically when transitioning from stop to proceed with caution), reducing overall processing resource consumption while maintaining collision avoidance capability.
Solution Approach 2:
The state machine uses feedback from sensor data to dynamically adjust processing requirements. When sensor data indicates a clear junction, the system can reduce processing intensity; when data indicates potential hazards, the system increases processing to evaluate exit conditions. This feedback-driven approach optimizes processing resource usage based on actual environmental conditions.
3Reliability
If the autonomous vehicle stops at red lights and waits for clear visibility, then the vehicle can safely execute right turns on red, but the traversal time increases
Solution Approach 1:
The vehicle performs periodic checks of sensor data and environmental conditions while in the stop state, rather than waiting for a fixed duration. The state machine evaluates exit conditions periodically, allowing the vehicle to proceed as soon as safety criteria are met, thus reducing unnecessary waiting time while maintaining safety through repeated verification of the environment.
Solution Approach 2:
The vehicle prepares for potential right turns on red by pre-evaluating junction conditions and having the state machine ready to transition to appropriate states. The system performs preliminary assessments of sensor data and environmental factors before committing to a stop, enabling faster response when safety conditions are met and reducing overall traversal time.
Data Source
AI summary
Techniques are discussed for controlling a vehicle, such as an autonomous vehicle, to navigate a junction in an environment. In some cases, the techniques can be used to navigate a turn at the junction or traverse through the junction. Operations include the vehicle detecting a stop signal and preparing the vehicle to stop at a location associated with the junction. The vehicle can determine a time to execute a maneuver and a visibility distance that a sensor can observe in the environment. A speed of the vehicle to execute the maneuver can be determined based on the time to execute the maneuver and the visibility distance.