Reusable Autonomous Skills Using Graphical Markers and Physical Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional programming methods for autonomous systems rely on hand-crafted, low-fidelity representations of environments, limiting their ability to reason about their state and environment, and requiring manual translation of data structures, which impedes the creation of autonomous systems capable of complex actions.
Innovation Solution
The use of explicit physical modeling and multi-function markers within a programming language allows for the creation of reusable skills by simulating physical environments, generating executable code to actuate physical devices based on marker positions and orientations, enabling autonomous systems to interact with their environment effectively.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If hand-crafted low-fidelity representations are used to represent the environment, then the programming process is simpler and faster, but the system's ability to reason about its state and environment is limited
Solution Approach 1:
The patent uses graphical markers that create a high-fidelity copy of the physical environment within the simulation. These markers capture precise position, orientation, and physical properties of objects, allowing the autonomous system to reason about its environment with accuracy while maintaining ease of programming through the graphical interface.
Solution Approach 2:
The patent adds a graphical visualization dimension to the programming interface. By displaying markers and environment representations in a graphical user interface, the system transforms complex spatial and physical relationships into visual information that is easier to program and reason about without sacrificing fidelity.
2Adaptability or versatility
If manual translation of data structures is required for each algorithm, then customization flexibility is increased, but development time and complexity increase significantly
Solution Approach 1:
The patent creates a universal data structure framework where graphical markers serve multiple functions across different algorithms and contexts. The same marker system is used for positioning, orientation, and physical property representation throughout the system, eliminating the need for manual translation between different data formats while maintaining customization through the graphical interface.
Solution Approach 2:
The patent introduces a graphical marker system as an intermediary between the physical environment and the software algorithms. This intermediary layer automatically handles data structure translation and conversion, allowing algorithms to work with standardized marker data while still accessing custom environmental information without manual translation efforts.
3Ease of operation
If I/O values are focused on without context, then programming is simpler, but the device cannot take action based on complicated needs requiring reasoning about state
Solution Approach 1:
The patent enhances specific I/O values with local contextual information through graphical markers. Each marker contains not just position and orientation data but also context about its relationship to other objects, physical properties, and environmental features. This allows the system to maintain simple I/O interfaces while providing rich contextual information for complex reasoning.
Data Source
AI summary
A computer-implemented method of engineering autonomous system with reusable skills includes displaying a graphical user interface simulating a physical environment. The graphical user interface depicts one or more simulated objects corresponding to one or more physical objects. Graphical markers are created on the simulated objects based on instructions provided by a user via the graphical user interface. The position and orientation of each graphical marker is determined with respect to the simulated objects. A skill function is created which comprises a functional description for using a controllable physical device to interact with the physical objects based on the position and orientation of each graphical marker. Executable code operable to perform the skill function is created and used to actuate the controllable physical device.