Remote Guidance Switching for Autonomous Vehicle Edge Cases
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in navigating through unpredictable situations that fall outside their programming or training, leading to impasses where they cannot continue forward progress, such as crowded environments or unexpected object movements, requiring intervention to overcome these 'edge cases'.
Innovation Solution
The system allows an autonomous robotic system to detect trigger conditions, transmit a remote guidance request to a server, and receive instructions to adjust its movement parameters, such as reducing buffer sizes and speed, enabling it to proceed cautiously under remote guidance, while reverting to previous settings if communication is lost or a threshold time is reached.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the autonomous vehicle maintains strict safety buffers and speed limits, then safety is improved, but forward progress is reduced
Solution Approach 1:
The system dynamically adjusts safety parameters (buffer sizes and speed limits) based on the operational context. When remote guidance is activated, the vehicle operates with reduced buffer sizes and speed limits compared to normal operation, allowing progress while maintaining adaptive safety. The parameters are not fixed but change based on whether remote guidance is active and what specific guidance instructions are received.
2Productivity
If the autonomous vehicle operates with reduced buffer sizes and speed under remote guidance, then forward progress is improved, but safety risks increase
Solution Approach 1:
A remote server acts as an intermediary between the vehicle's safety system and its motion control. The server receives requests for remote guidance, processes them with reduced safety parameters, and returns guidance instructions that balance progress and safety. This intermediary layer allows the vehicle to operate in a compromised safety state only when necessary and under remote supervision.
Solution Approach 2:
The system changes operational parameters (buffer sizes and speed limits) from their normal values to reduced values when remote guidance is activated. The buffer sizes are reduced from normal safety margins to smaller values that allow progress, and speed limits are adjusted accordingly. These parameter changes are reversible when remote guidance is deactivated.
3Adaptability or versatility
If the autonomous vehicle activates remote guidance mode, then ability to handle edge cases is improved, but system complexity increases
Solution Approach 1:
The complex decision-making logic for handling edge cases is extracted from the vehicle's onboard system and placed on a remote server. The vehicle only needs to detect trigger conditions and communicate with the server, while the server handles the complex analysis and generates guidance instructions. This extraction reduces the complexity burden on the vehicle itself.
Solution Approach 2:
The system implements a feedback loop where the vehicle monitors its operational state, detects when edge cases occur, requests remote guidance, receives instructions, and executes them. The continuous monitoring and communication provide feedback mechanisms that manage complexity through iterative interaction rather than requiring all complexity to be built into the vehicle's core system.
Data Source
AI summary
Disclosed herein are system, method, and computer program product embodiments for switching between local and remote guidance instructions for autonomous vehicles. For example, the method includes, in response to monitoring one or more actions of objects detected in a scene in which the autonomous robotic system is moving, causing the autonomous robotic system to slow or cease movement in the scene. The method includes detecting a trigger condition based on movement of the autonomous robotic system in the scene. In response to the one or more monitored actions and detecting the trigger condition, the method includes transmitting a remote guidance request to a remote server. After transmitting the remote guidance request, the method includes receiving remote guidance instructions from the remote server and causing the autonomous robotic system to begin operating according to the remote guidance instructions.