Cruise Control Plan Evaluation via Probabilistic Vehicle Behavior Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems face challenges in accurately evaluating the safety of cruise control plans for automatically-operated vehicles when nearby vehicles are manually operated, as their behaviors are difficult to predict due to constant changes.
Innovation Solution
A cruise control plan evaluation device that includes a behavior prediction unit, position prediction unit, and evaluation unit to predict the behavior and position of nearby vehicles, and assess the safety of cruise control plans by comparing predicted vehicle presence regions with contact and emergency avoidance regions using probability distributions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the system evaluates cruise control plans for automatically-operated vehicles, then the safety evaluation capability is improved, but the accuracy of predicting nearby vehicle behaviors deteriorates when those vehicles are manually-operated
Solution Approach 1:
The system changes the parameter representation from deterministic single-point predictions to probabilistic multi-point predictions. By predicting multiple possible positions with associated probabilities instead of single fixed positions, the system accommodates the unpredictable nature of manually-operated vehicles while maintaining reliable safety evaluation through the probability-based framework
Solution Approach 2:
The system transitions from static safety evaluation to dynamic probabilistic prediction. By continuously updating multiple possible future positions with varying probabilities based on current vehicle states and behaviors, the system adapts to changing conditions of manually-operated vehicles, making the safety evaluation both reliable and accurate
2Measurement precision
If the system predicts multiple possible positions of nearby vehicles, then the accuracy of safety evaluation is improved, but the computational complexity increases
Solution Approach 1:
The system applies partial action by focusing computational resources on predicting only the most probable future positions rather than exhaustively calculating all possible positions. By setting probability thresholds and limiting the number of predicted positions, the system achieves sufficient safety evaluation accuracy while controlling computational complexity
Data Source
AI summary
A cruise control plan evaluation device (10) that evaluates safety of a cruise control plan for an automatically-operated vehicle includes: a behavior prediction unit (16a) that predicts a behavior that may be exhibited by a nearby vehicle, which is present near the automatically-operated vehicle, at a given time point; a position prediction unit (16b) that predicts a position of the nearby vehicle after the given time point based on a position of the nearby vehicle at the given time point and the behavior predicted by the behavior prediction unit (16a); and an evaluation unit (20) that evaluates the safety of the cruise control plan based on the position of the nearby vehicle predicted by the position prediction unit (16b) and a position that is reached by the automatically-operated vehicle according to the cruise control plan.