Cooperative Teleoperation for Autonomous Vehicle Trajectory Refinement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in navigating unpredictable scenarios, leading to potential hazards such as sudden stops or unsafe maneuvers, as their autonomy systems may not be equipped to handle every possible driving situation.
Innovation Solution
The implementation of cooperative teleoperation systems, which allow an autonomy system to generate a planned trajectory while accepting input from a teleoperator for adjustments, enabling the system to refine and update the trajectory in real-time, allowing for continuous operation and safer navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If autonomous vehicle systems operate fully autonomously without human input, then automation extent is improved, but reliability deteriorates due to inability to handle unpredictable driving scenarios
Solution Approach 1:
The patent introduces a teleoperator as an intermediary between the autonomous vehicle system and the environment. The teleoperator receives information from the autonomous system and provides guidance or corrections when the system encounters unpredictable scenarios, serving as a mediator that bridges full automation and human control to maintain reliability while preserving automation extent.
2Reliability
If teleoperator control is implemented to handle unpredictable scenarios, then reliability is improved, but device complexity worsens due to integration of human-in-the-loop control
Solution Approach 1:
The system dynamically adjusts the level of teleoperator involvement based on the autonomous system's confidence and the unpredictability of the scenario. The teleoperator is engaged only when necessary, transitioning between autonomous operation and human guidance modes, which manages complexity by making the control architecture adaptive rather than statically complex.
3Reliability
If continuous teleoperator monitoring is implemented, then reliability is improved, but loss of time worsens due to human response delays in critical situations
Solution Approach 1:
Instead of continuous teleoperator monitoring, the system implements partial action by engaging the teleoperator only when the autonomous system encounters scenarios beyond its capability or confidence threshold. This selective engagement maintains reliability by providing human oversight when needed while avoiding the time loss associated with constant human monitoring and response.
Data Source
AI summary
An example method to control an autonomous vehicle includes receiving a first signal and receiving a second signal. The first signal includes a first set of parameters that define a planned trajectory for the autonomous vehicle. The second signal includes a second set of parameters that define a planned trajectory for the autonomous vehicle. The method also includes generating a third signal by modifying the first set of parameters of the first signal to include the second set of parameters of the second signal. The method also includes outputting the third signal.