Autonomous Vehicle Occlusion Reasoning via Visibility Grid

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Autonomous vehicles face challenges in navigating vehicle transportation networks due to occlusions, which can result in unobserved external objects, such as pedestrians or vehicles, being hidden from sensors, leading to safety and operational issues.

Innovation Solution

The method involves receiving sensor data, determining a visibility grid to identify unobserved regions, computing the probability of external object presence by comparing the grid to a map, and using this probability to traverse the network safely through scenario-specific operational control evaluation modules.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If sensors are used to detect the operational environment, then the vehicle can gather data for navigation, but occlusions cause some data to become unavailable

Engineering Contradiction:

Improvesensor data availabilityVSAvoidnavigation safety

Core Design Contradiction:

Loss of informationVSReliability

Solution Approach 1:

The system performs preliminary actions by determining a visibility grid and identifying unobserved regions before making navigation decisions. By proactively computing where objects might be hidden and estimating their presence probability, the system prepares for potential occlusions rather than reacting to them after detection failure

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The visibility grid acts as an intermediary representation between raw sensor data and navigation decisions. It mediates the information gap caused by occlusions by providing a structured probability map that indicates where external objects might exist despite being unobserved by sensors

Inventive Principle:

Principle #24Intermediary (Mediator)

2Productivity

If the vehicle traverses the transportation network using sensor data, then navigation can proceed, but unobserved regions create safety risks

Engineering Contradiction:

Improvenavigation efficiencyVSAvoidsafety risks from occlusions

Core Design Contradiction:

ProductivityVSObject-affected harmful factors

Solution Approach 1:

The system determines the visibility grid and computes unobserved regions in advance before executing navigation maneuvers. This preliminary analysis of occlusion risks allows the vehicle to plan safer trajectories while maintaining navigation progress

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system takes preliminary anti-action by identifying regions where objects might be hidden and adjusting navigation behavior to account for these potential hazards. By computing presence probabilities for unobserved regions, the system preemptively counteracts the harmful effect of occlusions on safety

Inventive Principle:

Principle #9Preliminary anti-action

Data Source

PatentUS11702070B2Autonomous vehicle operation with explicit occlusion reasoning

Publication Date: 2023.07.18 NISSAN MOTOR CO LTD

AI summary

Autonomous vehicle operation with explicit occlusion reasoning may include traversing, by a vehicle, a vehicle transporation network. Traversing the vehicle transportation network can include receiving, from a sensor of the vehicle, sensor data for a portion of a vehicle operational environment, determining, using the sensor data, a visibility grid comprising coordinates forming an unobserved region within a defined distance from the vehicle, computing a probability of a presence of an external object within the unobserved region by comparing the visibility grid to a map (e.g., a high-definition map), and traversing a portion of the vehicle transportation network using the probability. An apparatus and a vehicle are also described.