Human-Robot Collaboration Framework for Dynamic Task Switching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Small and medium-sized manufacturing enterprises face challenges in integrating robotic automation due to high production variability and the need for customization, as existing robotic systems are not adaptable to varying tasks and user interactions, limiting their effectiveness in SMEs and other domains like in-home assistance and collaborative surgery.
Innovation Solution
A generalizable framework for human-machine collaboration that enables dynamic adaptation and reuse of robotic capability representations, allowing robots to switch between tasks without retraining by composing robot capabilities with user interaction capabilities and utilizing tool affordances, tool movement primitives, and perceptual grounding templates to interact efficiently with users across diverse tasks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If robotic automation is implemented in SMEs with high product variability, then productivity is improved, but adaptability deteriorates because existing robotic systems cannot easily adapt to varying tasks
Solution Approach 1:
The robotic system implements dynamic task switching capability where the robot can transition between different task types (assembly, inspection, packaging) without requiring complete reprogramming. The system dynamically adapts its behavior based on the current task requirements, maintaining high productivity while achieving versatility through runtime configuration rather than static programming.
Solution Approach 2:
The patent creates a universal robotic platform that can perform multiple functions across different task domains. By implementing a common architecture that supports various task types through configurable parameters and modular task definitions, the system achieves multi-functionality that allows single robotic systems to serve diverse manufacturing needs in SMEs.
2Manufacturing precision
If complete reprogramming is required for task switching, then task precision is improved, but loss of time increases due to retraining requirements
Solution Approach 1:
The system performs preliminary configuration by pre-defining task templates and parameters that can be quickly instantiated. Rather than programming tasks from scratch, the system prepares reusable task definitions and configurations in advance, allowing rapid task switching while maintaining precision through proven task templates that have been previously validated.
Solution Approach 2:
The patent implements task copying capability where successfully defined tasks can be replicated and adapted for similar operations. Once a task is programmed and validated, it can be copied and modified for related tasks, preserving the precise programming work while enabling rapid deployment of similar tasks without complete reprogramming.
3Reliability
If specialized personnel and infrastructure are deployed for robotic automation, then reliability is improved, but device complexity increases
Solution Approach 1:
The robotic system implements self-service capabilities through automated task configuration, self-diagnosis, and adaptive learning. The system can automatically adjust its parameters and behavior based on task requirements without requiring specialized personnel for every configuration change, maintaining reliability through automated consistency while reducing the operational complexity burden on human operators.
Solution Approach 2:
By creating a universal control architecture that handles diverse task types through a common interface and configuration system, the patent reduces the need for multiple specialized systems. This unified approach maintains reliability through consistent error handling and monitoring across all tasks while simplifying the overall device complexity by consolidating functionality into a single platform.
Data Source
Figure 1A~1B
Figure 2
Figure 3A~3B
AI summary
Methods and systems for enabling human-machine collaborations include a generalizable framework (320. 350) that supports dynamic adaptation and reuse of robotic capability representations and human-machine collaborative behaviors. Specifically, a computer-implemented method (600, 700, 800) of enabling user-robot collaboration includes providing (614) a composition ( Figure 2, 400) of user interaction capabilities and a robot capability (Table 1) that, models a functionality of a robot (340, 380) for performing a type of task action based on a set of parameters; specializing (616, 714, 716} the robot capability with an information kernel that encapsulates the set of parameters; providing (712, 714, 716) a robot capability element, based on the robot capability and the information kernel and (718) interaction capability elements based on the user interaction capabilities; connecting (618, 800) the robot capability element to the interaction capability elements; providing (620), based on the interaction capability elements, user interfaces (310, 370, 500) to acquire user input (510, 520, 5.30, 540) associated with the set of parameters; and controlling (620), based on the user input and the information kernel, the functionality of the robot via the robot capability element to perform a task action of the type of task action.