Autonomous Vehicle Local Path Planning Around Parked Obstacles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles may deviate from lane centers due to parked vehicles, leading to prolonged waiting times without an effective local path planning modification scheme.
Innovation Solution
A local path planning system using an envelop graph structure and cost function to generate a trajectory that adapts to real-time obstacles, ensuring smooth and risk-aware path deviations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the autonomous vehicle waits for parked vehicles to move before continuing on a pre-determined path, then collision risk is reduced, but travel time increases significantly
Solution Approach 1:
The system performs preliminary local path planning modifications by generating an envelop graph structure that anticipates potential obstacles and pre-calculates alternative trajectories. This allows the vehicle to proactively prepare deviation paths rather than reactively waiting, reducing collision risk without significant time loss
Solution Approach 2:
The path planning system dynamically adapts the trajectory based on real-time obstacle detection and cost function evaluation. The envelop graph structure allows flexible modification of the pre-determined path, enabling the vehicle to dynamically deviate around parked vehicles and return to the optimal path, balancing safety and efficiency
2Reliability
If the autonomous vehicle deviates from lane center to avoid parked vehicles, then collision risk is reduced, but path optimality deteriorates
Solution Approach 1:
The system applies local path modifications only in specific regions where obstacles are detected, rather than deviating from the lane center throughout the entire journey. The envelop graph structure enables localized trajectory adjustments around parked vehicles while maintaining optimal lane center alignment in obstacle-free regions, preserving overall path efficiency
Solution Approach 2:
The cost function dynamically adjusts path evaluation parameters based on obstacle presence, weighing factors such as deviation distance, travel time, and safety margins. This allows the system to optimize the balance between collision avoidance and path efficiency by changing the parameters that define an 'optimal' path in different contextual scenarios
3Adaptability or versatility
If the autonomous vehicle uses a complex local path planning modification scheme, then path adaptability improves, but computational complexity increases
Solution Approach 1:
The path planning system segments the operating environment into discrete graph nodes and edges based on obstacle bounding boxes. This segmentation transforms the continuous path planning problem into a discrete graph traversal problem, enabling efficient computation of adaptive trajectories while maintaining high path adaptability to various obstacle configurations
Solution Approach 2:
The envelop graph structure serves as an intermediary representation between obstacle detection data and trajectory generation. This intermediate graph structure simplifies the computational task by pre-organizing valid path segments and their connections, reducing the complexity of real-time path adaptation while preserving versatility
Data Source
AI summary
According to one aspect, local path planning may be achieved using a sensor, a memory, a processor, a controller, and an actuator. The sensor may detect two or more objects within an operating environment. The memory may store one or more instructions. The processor may execute one or more of the instructions stored on the memory to perform one or more acts, actions, and/or steps. The processor may generate bounding box information for bounding boxes of the two or more objects. The processor may generate an envelop graph structure based on the bounding box information. The processor may generate a local path planning trajectory from a start region to a goal region within the envelop graph structure based on a cost function and the envelop graph structure. The controller may control the actuator to execute the local path planning trajectory for the autonomous vehicle.