Autonomous Vehicle Teleoperation for Event-Aware Trajectory Planning

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Autonomous vehicles struggle to effectively detect and respond to changing environments and events, such as lane closures or obstacles, without adequate information dissemination to other vehicles, leading to inefficiencies and safety risks.

Innovation Solution

Implementing a system that includes a fleet of autonomous vehicles connected to a service platform, utilizing sensors, localizers, perception engines, and planners to detect events, calculate optimal trajectories, and enable teleoperation when necessary, with redundancy in sensor fields to ensure reliable navigation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If autonomous vehicles operate independently without information sharing, then each vehicle maintains operational independence, but fleet-wide efficiency and safety are reduced due to lack of event dissemination

Engineering Contradiction:
Improvefleet-wide efficiencyVSAvoidevent information dissemination
Core Design Contradiction:
ProductivityVSLoss of information

Solution Approach 1:

The system implements feedback loops where sensor data and events detected by one autonomous vehicle are transmitted to the service platform, which then disseminates this information to other vehicles in the fleet. This creates a continuous information feedback cycle that improves fleet-wide awareness and efficiency without compromising individual vehicle independence.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The service platform acts as an intermediary between autonomous vehicles, receiving event data from sensors and distributing relevant information to other vehicles. This mediator approach enables information sharing across the fleet while maintaining operational independence of individual vehicles.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If teleoperation is used to handle complex events, then decision accuracy improves, but response time increases due to communication delays

Engineering Contradiction:
Improvedecision accuracyVSAvoidresponse time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary actions by pre-processing sensor data and identifying potential events before they require teleoperation intervention. The service platform pre-analyzes incoming data streams and prepares potential responses, so when teleoperation is needed, the decision-making process is already partially complete, reducing overall response time while maintaining accuracy.

Inventive Principle:
Principle #10Preliminary action

3Reliability

If sensor redundancy is implemented to ensure reliable navigation, then detection reliability improves, but system complexity and cost increase

Engineering Contradiction:
Improvedetection reliabilityVSAvoidsensor system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system merges sensor data from multiple sources and combines detection results through data fusion algorithms. By integrating information from various sensors and combining their outputs, the system achieves enhanced detection reliability without proportionally increasing system complexity, as the processing is centralized and optimized.

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentEP3371660B1Machine-learning systems and techniques to optimize teleoperation and/or planner decisions
Publication Date: 2026.04.01 ZOOX INC
  • EP3371660B1 patent drawingFigure 1
  • EP3371660B1 patent drawingFigure 2
  • EP3371660B1 patent drawingFigure 3A

AI summary

A system, an apparatus or a process may be configured to implement an application that applies artificial intelligence and/or machine-learning techniques to predict an optimal course of action (or a subset of courses of action) for an autonomous vehicle system (e.g., one or more of a planner of an autonomous vehicle, a simulator, or a teleoperator) to undertake based on suboptimal autonomous vehicle performance and/or changes in detected sensor data (e.g., new buildings, landmarks, potholes, etc.). The application may determine a subset of trajectories based on a number of decisions and interactions when resolving an anomaly due to an event or condition. The application may use aggregated sensor data from multiple autonomous vehicles to assist in identifying events or conditions that might affect travel (e.g., using semantic scene classification). An optimal subset of trajectories may be formed based on recommendations responsive to semantic changes (e.g., road construction).