Robotic Motion Planning With DOF-Group Sampling for Kinematic Changes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Robotic motion planning is hindered by complex, high-dimensional action spaces, brittleness, and domain-specific algorithms, making it computationally expensive and prone to errors, especially when environmental changes occur, such as additional degrees of freedom being introduced.
Innovation Solution
An underconstrained motion planner uses degree-of-freedom groups with entity-specific sampling strategies and views to generate motions for kinematic systems with an arbitrary number of degrees of freedom, allowing for modular and computationally efficient planning that adapts to changes without requiring re-engineering of the motion planning process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional motion planning algorithms are used with fixed domain assumptions, then the motion planning process is computationally tractable, but the system cannot adapt when environmental changes occur such as additional degrees of freedom are introduced
Solution Approach 1:
The patent segments the motion planning problem by introducing hierarchical levels of abstraction. The scene graph divides the environment into discrete objects and their properties, while the motion planning algorithm operates on simplified representations rather than the full complex state space. This segmentation allows the system to handle arbitrary degrees of freedom without exponentially increasing computational complexity.
Solution Approach 2:
The patent introduces intermediate data structures and representations that mediate between the complex physical environment and the motion planning algorithm. The scene graph acts as an intermediary layer that captures essential environmental features while filtering out unnecessary complexity. This intermediary representation enables the planner to adapt to environmental changes without requiring complete re-planning.
2Manufacturing precision
If manual programming is used to dictate robotic component movements, then precise control is achieved, but the process becomes tedious, time-consuming, and error-prone
Solution Approach 1:
The patent implements self-service through automatic scene graph construction and autonomous motion planning. The system automatically builds the scene graph from sensor data or environment descriptions, and the motion planner autonomously generates trajectories without manual programming. This self-service capability maintains precise control while eliminating the time-consuming and error-prone manual programming process.
Solution Approach 2:
The patent performs preliminary actions by pre-processing the environment into a scene graph structure before motion planning begins. This preliminary representation captures all necessary environmental information in an organized format, allowing the motion planner to efficiently generate precise trajectories without time-consuming manual programming during execution.
3Productivity
If the motion planning algorithm assumes a fixed number of degrees of freedom, then computational efficiency is maintained, but the algorithm becomes unusable when system components are upgraded with additional degrees of freedom
Solution Approach 1:
The patent implements dynamics by making the scene graph and motion planning process adaptive to changing system configurations. Rather than assuming a fixed number of degrees of freedom, the system dynamically constructs the scene graph to reflect the actual environment, including any additional degrees of freedom from upgraded components. The motion planner then operates on this dynamic representation, maintaining computational efficiency while accommodating system changes.
4Reliability
If exhaustive search of all candidate joint configurations is performed, then complete motion plans are generated, but the computational cost becomes prohibitive in high-dimensional action spaces
Solution Approach 1:
The patent applies local quality by focusing computational resources on locally relevant portions of the configuration space. The scene graph enables the planner to identify and prioritize locally important features and constraints, generating motion plans that are complete with respect to essential requirements without exhaustively searching the entire high-dimensional space. This local focus maintains reliability while reducing computational resource consumption.
Data Source
AI summary
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating motions for components in a robotic operating environment. One of the methods includes receiving a request to generate a motion for a kinematic system having a plurality of connected entities. An entity-specific sampling module for each of multiple degree-of-freedom (DOF) groups representing respective entities of the kinematic system is identified. A plurality of joint configuration samples are generated according to an ordering of a plurality of nonfunctional DOF groups using a respective entity-specific sampling module for each nonfunctional DOF group. A final joint configuration sample is generated for one or more one or more control points using a respective entity-specific sampling module for a functional DOF group. A motion comprising a sequence of respective joint configuration samples from each of the plurality of DOF groups is generated.