Autonomous Vehicle Trajectory Scoring for Adaptive Behavior Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional autonomous vehicle behavior planning systems are inflexible and fail to optimally adjust trajectories based on changing environmental conditions, leading to sub-optimal decisions that do not account for dynamic inputs from various functionalities such as collision avoidance and lane planning.
Innovation Solution
A behavior planning system that evaluates multiple hypothetical trajectories concurrently, using optimization scores from various components like collision avoidance, route planning, and lane planning to select the best trajectory, considering competing priorities like safety, comfort, and efficiency, and updates trajectories iteratively to reflect dynamic environmental changes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If conventional behavior planning systems select a route with the lowest travel time and then pick a lane plan that follows the route, then travel time is minimized, but the system becomes inflexible and cannot optimally adjust trajectories based on changing environmental conditions
Solution Approach 1:
The system dynamically adjusts trajectory parameters by allowing multiple hypothetical trajectories to be concurrently evaluated and by enabling different components (collision avoidance, route planning, lane planning) to provide optimization scores that can change based on real-time environmental conditions, making the planning system adaptive rather than static
Solution Approach 2:
The system changes trajectory parameters by integrating optimization scores from multiple components that quantify different priorities (safety, comfort, efficiency), allowing the selected trajectory to be optimally adjusted based on changing environmental conditions rather than following a fixed predetermined path
2Device complexity
If behavior planning determines vehicle behaviors separately from collision avoidance, then the planning process is simpler, but collision avoidance becomes reactive rather than proactive and overwrites the trajectory
Solution Approach 1:
The system merges behavior planning and collision avoidance into a unified framework where both functions concurrently evaluate multiple hypothetical trajectories and provide optimization scores, eliminating the need for separate deterministic processes and reactive overwrites while integrating safety considerations directly into trajectory selection
Solution Approach 2:
The system implements feedback by having collision avoidance provide optimization scores for multiple hypothetical trajectories based on safety considerations, allowing the planning system to proactively select safe trajectories rather than reactively correcting unsafe ones, with the feedback loop continuously updating trajectory evaluations
3Reliability
If multiple hypothetical trajectories are concurrently evaluated with optimization scores from multiple components, then trajectory selection becomes more optimal and safe, but the computational complexity increases
Solution Approach 1:
The system segments the trajectory evaluation process into multiple independent components (collision avoidance, route planning, lane planning), each providing optimization scores for different aspects of trajectory quality, allowing parallel computation and modular complexity management rather than a single monolithic evaluation system
Solution Approach 2:
The optimization score framework serves multiple functions simultaneously by quantifying different priorities (safety, comfort, efficiency) from various components, allowing a single unified scoring mechanism to handle diverse evaluation criteria and enable comprehensive trajectory comparison across multiple dimensions
Data Source
AI summary
Embodiments of the present disclosure relate to behavior planning for autonomous vehicles. The technology described herein selects a preferred trajectory for an autonomous vehicle based on an evaluation of multiple hypothetical trajectories by different components within a planning system. The various components provide an optimization score for each trajectory according to the priorities of the component and scores from multiple components may form a final optimization score. This scoring system allows the competing priorities (e.g., comfort, minimal travel time, fuel economy) of different components to be considered together. In examples, the trajectory with the best combined score may be selected for implementation. As such, an iterative approach that evaluates various factors may be used to identify an optimal or preferred trajectory for an autonomous vehicle when navigating an environment.