Hybrid Robot Trajectory Generation for Smooth Path Transitions

Solution Overview

Problem

Robots configured to automatically determine trajectories may suffer from inefficiencies in path planning, particularly in transitioning between segments of a trajectory, leading to suboptimal motion states and potential disruptions in motion.

Innovation Solution

A hybrid trajectory generation method is employed, where a real-time trajectory generator creates an initial segment based on kinematic constraints, and a trajectory optimizer generates a subsequent segment using anticipated motion states of the robot's actuators, ensuring a smooth handoff and optimization of the overall path.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If a robot uses automatic trajectory determination based on sensed environmental conditions, then the robot can operate autonomously without user manipulation, but the trajectory planning efficiency deteriorates due to suboptimal motion states and disruptions in motion

Engineering Contradiction:

Improveautonomous trajectory determinationVSAvoidtrajectory planning efficiency

Core Design Contradiction:

Extent of automationVSProductivity

Solution Approach 1:

The trajectory is divided into multiple segments, with different portions generated by different methods. The first portion uses real-time trajectory generation for immediate responsiveness, while the second portion uses optimization-based generation for improved efficiency. This segmentation allows the system to combine the advantages of both approaches while mitigating their individual weaknesses.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system pre-generates an optimized trajectory portion before the robot begins execution. This preliminary optimization is performed based on anticipated motion states at the handoff point, allowing the robot to switch to a pre-computed optimal path that improves overall trajectory planning efficiency while maintaining autonomous operation.

Inventive Principle:

Principle #10Preliminary action

2Speed

If a robot uses real-time trajectory generation for immediate responsiveness, then the robot can quickly begin traversal toward target waypoints, but the trajectory optimality deteriorates compared to optimized trajectories

Engineering Contradiction:

Improveresponse speedVSAvoidtrajectory optimality

Core Design Contradiction:

SpeedVSManufacturing precision

Solution Approach 1:

The trajectory is divided into multiple segments, with different portions generated by different methods. The first portion uses real-time trajectory generation for immediate responsiveness, while the second portion uses optimization-based generation for improved efficiency. This segmentation allows the system to combine the advantages of both approaches while mitigating their individual weaknesses.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Instead of optimizing the entire trajectory in real-time (which would be computationally expensive), the system applies optimization only to the second portion of the trajectory after the handoff point. This partial optimization approach achieves improved trajectory optimality without sacrificing the real-time responsiveness needed for the first portion.

Inventive Principle:

Principle #16Partial or excessive action

3Adaptability or versatility

If a robot transitions between trajectory segments, then the robot can follow complex multi-stage paths, but motion disruptions occur at the handoff points between segments

Engineering Contradiction:

Improvetrajectory segment transitionVSAvoidmotion smoothness

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The system pre-generates an optimized trajectory portion before the robot begins execution. This preliminary optimization is performed based on anticipated motion states at the handoff point, allowing the robot to switch to a pre-computed optimal path that improves overall trajectory planning efficiency while maintaining autonomous operation.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The trajectory optimizer uses anticipated motion states at the handoff point as feedback to generate the second portion of the trajectory. This feedback mechanism ensures that the optimized portion is smoothly connected to the real-time generated portion, eliminating motion disruptions at the transition point while still enabling complex multi-stage path following.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS10035266B1Generating robot trajectories using a real time trajectory generator and a path optimizer

Publication Date: 2018.07.31 GDM HOLDING LLC

AI summary

Methods, apparatus, systems, and computer readable media are provided for generating a trajectory for a robot to enable a reference point of the robot to reach a target waypoint. A real time trajectory generator is utilized to generate a first segment of a trajectory toward a target waypoint. While the robot is traversing the first segment of the trajectory, a trajectory optimizer is utilized to generate a second segment of the trajectory from an “end point” of the first segment (an actual end of the first segment or a defined “hand off” point) until the target waypoint is reached (or until an intermediate waypoint is reached). The trajectory optimizer may utilize anticipated motion states of one or more actuators of the robot at the end point of the first segment in generating the second segment.