Autonomous Vehicle Motion Planning Around Predicted Object Paths
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in efficiently and safely navigating around proximate objects, such as vehicles and pedestrians, due to limitations in real-time motion planning and collision avoidance systems.
Innovation Solution
An autonomous vehicle system that processes sensor data to identify objects of interest, generates cost data for adjusting its motion to follow or lead these objects, and determines a motion plan to optimize its trajectory based on predicted paths and constraints, allowing it to proactively control its motion and avoid collisions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the autonomous vehicle uses basic sensor data processing for motion planning, then the system complexity is low, but the collision avoidance capability and safety are insufficient
Solution Approach 1:
The motion planning system is segmented into multiple independent modules: sensor data acquisition module, object detection module, cost data generation module, and motion plan determination module. Each module handles a specific function, allowing the system to achieve high reliability through specialized processing while managing complexity through functional decomposition.
Solution Approach 2:
The system performs preliminary actions by generating cost data that represents the effect of controlling vehicle motion before actual motion execution. This predictive cost data generation allows the vehicle to evaluate multiple potential motion paths in advance and select the safest option, improving collision avoidance capability while maintaining systematic control.
2Measurement precision
If the autonomous vehicle processes detailed sensor data for each proximate object, then the object identification accuracy improves, but the computational time and processing load increase
Solution Approach 1:
The system applies local quality by generating cost data specifically for identified objects of interest rather than processing all sensor data uniformly. The cost data represents the localized effect of motion control on each identified object, allowing accurate object identification and motion planning while reducing overall computational load by focusing processing on relevant objects only.
3Manufacturing precision
If the autonomous vehicle generates comprehensive cost data for motion control, then the motion planning accuracy improves, but the computational resources and processing time increase
Solution Approach 1:
The system implements partial action by generating cost data that represents only the necessary effect of motion control on identified objects of interest, rather than computing all possible motion parameters. This selective cost data generation provides sufficient motion planning accuracy while reducing computational resource consumption by focusing on critical motion control aspects.
Data Source
AI summary
Systems and methods for controlling the motion of an autonomous are provided. In one example embodiment, a computer implemented method includes obtaining, by one or more computing devices on-board an autonomous vehicle, data associated with one or more objects that are proximate to the autonomous vehicle. The data includes a predicted path of each respective object. The method includes identifying at least one object as an object of interest based at least in part on the data associated with the object of interest. The method includes generating cost data associated with the object of interest. The method includes determining a motion plan for the autonomous vehicle based at least in part on the cost data associated with the object of interest. The method includes providing data indicative of the motion plan to one or more vehicle control systems to implement the motion plan for the autonomous vehicle.