Robot Behavior Graph Planning to Eliminate Control Downtime
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional robotic control planners require downtime to compute execution plans after preceding behaviors complete, leading to inefficiencies in robot operations.
Innovation Solution
A preemptive planning system that uses a coordination module and graphs of behaviors to predict and plan for downstream actions during upstream behavior execution, allowing for reduced downtime by generating and executing plans in advance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional robotic control planners compute execution plans after preceding behaviors complete, then the system ensures accurate planning based on actual outcomes, but the system experiences downtime during plan calculation
Solution Approach 1:
The system performs preliminary planning by computing execution plans for downstream behaviors while upstream behaviors are still executing. The coordination module receives predictions from upstream behaviors and generates plans in advance, so that when the upstream behavior completes, the plan is already ready for immediate execution, eliminating downtime while maintaining reliability through prediction-based planning
Solution Approach 2:
The system dynamically adjusts planning timing by transitioning from static post-completion planning to dynamic preemptive planning. The coordination module continuously monitors upstream behavior execution and generates plans at optimal moments during execution, allowing the system to adapt plan generation timing to actual runtime conditions and minimize idle time
2Ease of operation
If the system waits for upstream behavior completion before planning downstream actions, then the system maintains simple sequential control logic, but the system loses operational efficiency
Solution Approach 1:
The coordination module serves as an intermediary that manages the complexity of preemptive planning while keeping upstream and downstream behaviors simple. It receives predictions from upstream behaviors, computes downstream plans, and handles the coordination logic, allowing individual behaviors to remain simple while the overall system achieves high operational efficiency through centralized intelligent coordination
Data Source
AI summary
A method for preemptive control planning can include: optionally determining a graph that defines dependencies between behaviors; executing an execution plan for an executing behavior; generating a set of predictions with the executing behavior; propagating the set of predictions to child behaviors of the executing behavior; determining child execution plans and child predictions with the child behaviors; repeating the above for descendant behaviors of each child behavior; determining a realized world state associated with completion of the execution plan; and executing a child execution plan associated with a world state prediction matching the realized world state.