Autonomous Vehicle Trajectory Planning for Obstacle Avoidance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in navigating through environments with dynamic and static obstacles, as existing methods often result in unnecessary stops and delays, and may not efficiently determine safe trajectories to reach destinations while adhering to traffic rules.
Innovation Solution
The system determines a target trajectory by analyzing map data and sensor information to identify obstacles and calculate costs associated with different actions, allowing the vehicle to safely traverse through updated drivable regions, such as using an oncoming lane to circumvent obstacles, thereby optimizing navigation and safety.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the autonomous vehicle uses traditional obstacle avoidance methods, then safety is maintained, but unnecessary stops and delays occur
Solution Approach 1:
The system dynamically adjusts the drivable region boundaries based on real-time obstacle detection and classification. When obstacles are detected, the system dynamically computes alternative trajectories that may temporarily expand into adjacent lanes or regions, then returns to the original path, creating a dynamic navigation approach that adapts to changing conditions rather than relying on static lane constraints
Solution Approach 2:
The system adds the dimension of temporal sequencing to obstacle avoidance by implementing a state machine with multiple states (approach, prepare to stop, stop, proceed with caution, go). This temporal dimension allows the vehicle to progress through structured phases of response, enabling more nuanced decision-making that can maintain motion while ensuring safety, rather than relying solely on spatial lane constraints
2Reliability
If the autonomous vehicle strictly adheres to designated drivable regions, then traffic rules are followed, but navigation efficiency decreases
Solution Approach 1:
The system performs preliminary assessment of alternative trajectories by computing costs for different actions (staying in lane versus changing to oncoming lane) before executing the maneuver. The state machine transitions through preparatory states (approach, prepare to stop) that allow the system to evaluate conditions and plan the optimal path in advance, ensuring traffic rules are considered before deviating from the original drivable region
Solution Approach 2:
The system inverts the traditional approach by allowing temporary violation of lane boundaries (using the oncoming lane) when obstacles block the original path, with the understanding that the vehicle will return to the correct lane after passing the obstacle. This inversion prioritizes overall navigation efficiency while maintaining safety through structured decision-making and cost analysis
3Adaptability or versatility
If the autonomous vehicle determines multiple possible actions, then navigation flexibility increases, but computational complexity increases
Solution Approach 1:
The system segments the navigation decision-making process into distinct states within a state machine (approach, prepare to stop, stop, proceed with caution, go). Each state represents a specific phase of obstacle response with defined transition conditions, breaking down the complex decision-making process into manageable segments that can be evaluated systematically rather than considering all possibilities simultaneously
Data Source
AI summary
A vehicle can traverse an environment along a first region and detect an obstacle impeding progress of the vehicle. The vehicle can determine a second region that is adjacent to the first region and associated with a direction of travel opposite the first region. A cost can be determined based on an action (e.g., an oncoming action) to utilize the second region to overtake the obstacle. By comparing the cost to a cost threshold and/or to a cost associated with another action (e.g., a “stay in lane” action), the vehicle can determine a target trajectory that traverses through the second region. The vehicle can traverse the environment based on the target trajectory to avoid, for example, the obstacle in the environment while maintaining a safe distance from the obstacle and/or other entities in the environment.