Autonomous Pullover Speed Reasoning for Occluded Parking Spots
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in identifying suitable pullover locations, especially when these locations are occluded or not currently visible, leading to potential discomfort for passengers and other road users due to premature slowing or hard braking.
Innovation Solution
The vehicle's computing system receives sensor data to calculate a cost for each pullover location, considering occluded areas by applying a field of view restriction and predicting offsets, allowing it to select the best location and adjust speed accordingly to minimize discomfort and ensure safe maneuvers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If the vehicle evaluates pullover locations at a fixed distance away to avoid excessively fast lateral shifting and hard braking, then passenger comfort is improved, but the vehicle may unnecessarily restrict where it can actually pull over and may not identify suitable spots due to occlusions
Solution Approach 1:
The system dynamically adjusts the evaluation distance for pullover locations based on vehicle dynamics and environmental conditions. Instead of using a fixed distance constraint, the system adapts the search radius and evaluation criteria in real-time, allowing the vehicle to consider locations closer or farther away depending on current speed, acceleration capabilities, and visibility conditions, thus resolving the contradiction between comfort and flexibility
Solution Approach 2:
The system performs preliminary evaluation of potential pullover locations at greater distances before the vehicle reaches them. By pre-identifying and assessing multiple candidate locations with different distance constraints, the system prepares a hierarchy of options that can be selected based on real-time conditions, enabling both comfort-oriented and flexibility-oriented choices
2Device complexity
If the vehicle uses limited sensor availability and basic field of view to identify pullover locations, then system complexity is reduced, but the likelihood of identifying suitable spots is reduced due to occlusions
Solution Approach 1:
The system introduces virtual or predicted offset representations as intermediaries between the limited sensor data and the pullover location decision. By creating probabilistic models of occluded areas and using these as intermediate representations, the system can reason about hidden locations without requiring additional physical sensors, thus maintaining low complexity while improving reliability
Solution Approach 2:
The system replaces physical sensor expansion with computational methods for detecting and reasoning about occluded areas. Instead of adding more sensors to see around occlusions, the system uses algorithmic approaches to predict what might be hidden and evaluates those predictions, substituting mechanical sensor addition with intelligent processing
3Reliability
If the vehicle slows down prematurely to check for occluded parking spots, then identification of hidden locations is improved, but passenger discomfort increases due to unnecessary slowing
Solution Approach 1:
The system applies partial slowing or speed adjustment only in specific conditions and for specific durations needed to gather sufficient sensor data about occluded areas, rather than premature or excessive slowing. By calibrating the degree and duration of speed reduction to the actual information-gathering needs, the system achieves adequate detection accuracy while minimizing passenger discomfort
Data Source
AI summary
The technology involves pullover maneuvers for vehicles operating in an autonomous driving mode. A vehicle operating in an autonomous driving mode is able to identify parking locations that may be occluded or otherwise not readily visible. A best case estimation for any potential parking locations, including partially or fully occluded areas, is compared against predictions for identified visible parking locations. This can include calculating a cost for each potential parking location and comparing that cost to a baseline cost. Upon determining that an occluded location would provide a more viable option than any visible parking locations, the vehicle is able to initiate a driving adjustment (e.g., slow down) prior to arriving at the occluded location. This enables the vehicle to minimize passenger discomfort while also providing notice to other road users of an intent to pull over.