AV ETA Estimation Using Reroute Probabilities
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in accurately estimating trip duration due to frequent rerouting caused by maneuver failures, which are influenced by various factors including traffic conditions, environmental conditions, and driving maneuver complexity, leading to deviations in estimated time of arrival (ETA) figures.
Innovation Solution
The solution involves calculating a weighted sum of ETAs for various routes based on reroute likelihoods, which are determined by factors such as maneuver success probabilities, lane position, and environmental conditions, to provide an accurate ETA even in areas with sparse data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If autonomous vehicles use conventional routing methods, then the navigation system is simple, but the estimated time of arrival (ETA) is inaccurate due to frequent rerouting from maneuver failures
Solution Approach 1:
The system performs preliminary actions by calculating reroute probabilities and adjusting ETA estimates before actual rerouting events occur. By pre-computing the likelihood of maneuver failures and their impact on trip duration, the system proactively compensates for expected reroutes, improving ETA accuracy without requiring complex real-time responses when reroutes actually happen.
Solution Approach 2:
The routing system dynamically adjusts ETA estimates based on changing conditions by incorporating reroute probabilities that reflect current traffic conditions, environmental factors, and maneuver complexity. This dynamic adjustment allows the system to adapt to varying risk levels throughout the journey, maintaining accuracy without requiring a completely complex re-routing architecture.
2Measurement precision
If autonomous vehicles account for reroute probabilities in ETA calculations, then ETA accuracy improves, but the computational complexity increases
Solution Approach 1:
The system segments the routing problem into manageable components by calculating reroute probabilities for individual maneuvers or route segments rather than attempting to compute all possible reroute scenarios simultaneously. This segmentation allows the complex computational task to be broken down into smaller, more tractable calculations that can be performed efficiently.
Solution Approach 2:
The system changes parameters by using probabilistic models and statistical methods to estimate reroute impacts, rather than requiring exhaustive simulation of all possible reroute scenarios. By transforming the problem from a deterministic to a probabilistic framework, the system achieves accurate ETA estimates with reduced computational burden.
3Reliability
If autonomous vehicles frequently reroute due to maneuver failures, then safety is maintained, but trip duration increases
Solution Approach 1:
The system performs preliminary actions by identifying high-risk maneuvers and pre-calculating alternative routes before maneuver failures occur. By having reroute plans ready in advance for probable failure points, the system can execute reroutes more efficiently, minimizing the time lost when rerouting becomes necessary while maintaining safety through proactive risk management.
Data Source
AI summary
The subject disclosure relates to ways to improve route duration calculations e.g., estimated time of arrival (ETA) approximations, by taking consideration of reroute probabilities along a given vehicle path. In some aspects, the disclosed technology encompasses a process including steps for identifying a route between a first destination to a second destination, determining a reroute likelihood associated with at least one AV maneuver along the route, and calculating an estimated time of arrival (ETA) based on the reroute likelihood associated with at least one AV maneuver. Systems and machine-readable media are also provided.