Autonomous Vehicle Motion Planning With Predicted Blocking Actions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in accurately predicting and responding to the motion trajectories of objects in their surroundings, leading to potential safety issues and inefficiencies in navigation.
Innovation Solution
A computer-implemented method and system that utilizes a blocking model and vehicle action model to determine whether objects are blocking the vehicle's path and to plan appropriate actions at each time step, incorporating sensor data, map data, and machine-learning algorithms to optimize vehicle motion planning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If autonomous vehicles use basic sensor data processing without predictive modeling, then the system complexity is low, but the safety and collision avoidance capability deteriorates
Solution Approach 1:
The system performs preliminary action by predicting future motion trajectories of objects before collisions can occur. The predictive motion trajectory model forecasts where objects will be in future time steps, allowing the vehicle to plan avoidance maneuvers in advance rather than reacting to current positions only.
Solution Approach 2:
The system applies dynamics by transitioning from static sensor data processing to dynamic predictive modeling. The motion trajectory predictions adapt to changing object velocities and directions, and the vehicle action sequences are dynamically generated based on predicted blocking scenarios at future time steps.
2Reliability
If autonomous vehicles use detailed predicted motion trajectories for multiple objects, then the collision avoidance capability improves, but the computational complexity and processing time increases
Solution Approach 1:
The system segments the motion planning problem into discrete time steps and individual object predictions. Each object's trajectory is predicted independently for multiple future time steps, and vehicle actions are determined for each time step separately, allowing parallel processing and efficient computation.
Solution Approach 2:
The system changes parameters by using discrete time step predictions rather than continuous trajectory modeling. The predictive model generates motion trajectories at specific future time steps, and the vehicle action sequence is generated based on blocking assessments at these discrete points, reducing computational burden while maintaining safety.
3Productivity
If autonomous vehicles implement granular motion control at multiple time steps, then the navigation efficiency improves, but the control system complexity increases
Solution Approach 1:
The control system achieves dynamics by generating adaptive vehicle action sequences for multiple future time steps. The system determines appropriate actions (proceed, stop, change lane) at each time step based on predicted object trajectories and blocking scenarios, allowing flexible and efficient navigation responses to changing environmental conditions.
Solution Approach 2:
The system applies self-service by using the predictive motion trajectory model to automatically assess blocking scenarios and generate appropriate vehicle actions without continuous human intervention. The blocking model and vehicle action model work together to autonomously determine navigation decisions based on predicted future states.
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 data associated with an object within a surrounding environment of an autonomous vehicle. The data associated with the object is indicative of a predicted motion trajectory of the object. The method includes determining a vehicle action sequence based at least in part on the predicted motion trajectory of the object. The vehicle action sequence is indicative of a plurality of vehicle actions for the autonomous vehicle at a plurality of respective time steps associated with the predicted motion trajectory. The method includes determining a motion plan for the autonomous vehicle based at least in part on the vehicle action sequence. The method includes causing the autonomous vehicle to initiate motion control in accordance with at least a portion of the motion plan.