Remote AV Relocation Using Multi-Point Maneuvers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomous vehicles face challenges in efficiently relocating to target poses, particularly when stuck due to strict constraints of structured planners, and there is a need for remote assistance systems to facilitate complex maneuvers like multi-point maneuvers.
Innovation Solution
A remote relocation system for autonomous vehicles that includes a freespace planner with relaxed constraints, a remote vehicle interface, and a relocation state machine, allowing remote advisors to request and execute relocation plans through a graphical user interface, leveraging motion planners like structured and freespace planners for flexible path generation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If structured planners with strict constraints are used for autonomous vehicle path planning, then safety and rule compliance are improved, but the ability to perform complex maneuvers and relocate from constrained positions deteriorates
Solution Approach 1:
The system segments the path planning function into two distinct planners: a structured planner that enforces safety rules and constraints, and a freespace planner that optimizes for maneuverability and relocation. This segmentation allows each planner to specialize in its strength without compromise - the structured planner maintains safety while the freespace planner enables complex maneuvers when needed
Solution Approach 2:
The system dynamically switches between the structured planner and freespace planner based on the operational context and vehicle state. When the vehicle is in a normal operating state, the structured planner is used for safety compliance. When the vehicle becomes stuck or needs to perform complex relocation maneuvers, the system transitions to the freespace planner, which has relaxed constraints and can generate creative path solutions
2Productivity
If autonomous vehicles rely solely on automated planning algorithms, then operational efficiency is improved, but the ability to handle complex relocation scenarios deteriorates
Solution Approach 1:
The system introduces a remote vehicle interface and freespace planner as an intermediary between the automated planning system and complex relocation scenarios. When the automated structured planner cannot find a valid path due to strict constraints, the freespace planner with relaxed constraints acts as a mediator to generate feasible relocation paths, which can then be executed by the vehicle or refined by remote operators
Solution Approach 2:
The autonomous vehicle system performs self-service by automatically switching between planning modes and executing relocation maneuvers without requiring constant remote operator intervention. The vehicle can autonomously determine when it is stuck, activate the freespace planner, and execute the generated relocation path, maintaining operational efficiency while handling complex scenarios
Data Source
AI summary
It may be desirable for a remote advisor to request an AV to relocate to a target relocation pose. In some cases, reaching a target relocation pose may involve a multi-point maneuver. Ability to perform relocation that involves a multi-point maneuver offers flexibility for the AV to maneuver around double-parked vehicles, to avoid obstacles, to aid a reroute when a route becomes unnavigable, etc. To support relocation that involves performing multi-point maneuvers, the planning stack may be modified to include a motion planner that can generate output plans that involve the AV going forward and in reverse. Moreover, the vehicle control stack may publish vehicle controls information as feedback information to the motion planner and the remote requestor, so that the motion planner and the remote requestor can be informed of the state of the AV.