Legged Robot Maneuver Scripting for Compatible Joint Commands
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for programming robot movements are time-consuming and require hardcoding, limiting the ability to rapidly author and modify robot behavior, and often fail to account for environmental and physical constraints, leading to potential damage to the robot or its environment.
Innovation Solution
A method and system that allow users to generate a maneuver script for legged robots by combining and sequencing existing maneuvers without hardcoding, using a user interface to create a movement routine that accounts for joint control and environmental factors, with a computing system to determine combined maneuvers and generate joint commands based on associated costs and compatibility.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional hardcoded programming methods are used to program robot movements, then control precision and reliability are improved, but programming time and complexity increase significantly
Solution Approach 1:
The patent segments the robot control program into reusable maneuver modules that can be independently defined, stored in a library, and combined through scripting. Each maneuver represents a discrete, pre-tested movement primitive that maintains reliability while enabling rapid composition of complex behaviors through high-level scripts rather than low-level hardcoded commands.
Solution Approach 2:
The patent implements preliminary action by pre-defining and validating maneuver templates with associated cost functions and constraints before runtime. These pre-programmed maneuvers include built-in safety checks and physical constraints, allowing rapid deployment of reliable behaviors without re-programming each specific movement from scratch.
2Adaptability or versatility
If multiple maneuvers are combined to create complex behaviors, then robot versatility and capability are improved, but computational complexity and coordination difficulty increase
Solution Approach 1:
The patent merges multiple maneuvers into composite behaviors through maneuver scripts that sequence and coordinate individual maneuvers. The system combines simple, well-defined maneuver primitives into complex behaviors by layering them in scripts, where each maneuver's entry and exit states are explicitly defined to ensure proper sequencing and reduce coordination complexity.
Solution Approach 2:
The patent uses parameter changes by associating cost functions with each maneuver that can be weighted and adjusted to prioritize certain behaviors over others. The cost function parameters allow the robot to adaptively select and combine maneuvers based on task requirements, environmental constraints, and performance objectives without increasing the fundamental complexity of individual maneuver definitions.
3Ease of operation
If maneuver scripts are used to enable rapid programming, then ease of operation and productivity are improved, but ensuring compatibility and feasibility of combined maneuvers becomes more difficult
Solution Approach 1:
The patent implements feedback mechanisms that automatically verify maneuver compatibility when composing scripts. The system checks entry and exit states of maneuvers to ensure proper sequencing, validates that combined maneuvers satisfy physical constraints, and provides feedback to the programmer about compatibility issues. This automated verification maintains reliability while preserving the ease of script-based programming.
Solution Approach 2:
The patent applies beforehand cushioning by pre-defining maneuver templates with explicit entry and exit state specifications and associated cost functions that encode physical constraints and safety requirements. These pre-established boundaries and constraints act as protective buffers that prevent incompatible maneuvers from being combined, ensuring feasibility before the actual composition occurs.
Data Source
AI summary
The disclosure provides a method for generating a joint command. The method includes receiving a maneuver script including a plurality of maneuvers for a legged robot to perform where each maneuver is associated with a cost. The method further includes identifying that two or more maneuvers of the plurality of maneuvers of the maneuver script occur at the same time instance. The method also includes determining a combined maneuver for the legged robot to perform at the time instance based on the two or more maneuvers and the costs associated with the two or more maneuvers. The method additionally includes generating a joint command to control motion of the legged robot at the time instance where the joint command commands a set of joints of the legged robot. Here, the set of joints correspond to the combined maneuver.