Robot Environment Modeling With Oversized Cable-Aware Geometry
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing motion planning systems for robots in three-dimensional operational environments fail to accurately account for the robot's own structure, particularly cables and other attached features, leading to potential collisions and inefficient path planning due to incomplete digital representations.
Innovation Solution
A method is introduced to generate an oversized digital representation of the robot, which includes its appendage and attached structures like cables, to filter out the robot's volume from the operational environment model, ensuring that regions occupied by the robot are marked as unoccupied, thereby preventing self-blocking and improving motion planning accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the robot's digital representation includes only its main body without attached structures, then the digital representation is simpler and faster to process, but collision detection accuracy deteriorates because cables and other attached features are not accounted for
Solution Approach 1:
The robot's digital representation is segmented into multiple components: the main body and separate attached structures such as cables. Each component can be independently modeled and processed, allowing the system to account for collision risks from cables without requiring a completely complex unified model of the entire robot system.
Solution Approach 2:
The patent extends the digital representation from three-dimensional spatial coordinates to four-dimensional space-time representation. This allows the system to model the dynamic positions of cables and other attached structures over time, improving collision detection accuracy by capturing temporal variations in robot configuration without permanently increasing spatial complexity.
2Measurement precision
If the digital representation includes detailed models of all attached structures like cables, then collision detection accuracy improves, but computational speed deteriorates due to increased processing complexity
Solution Approach 1:
The system applies partial action by selectively modeling only those attached structures that pose collision risks in the current operational context. Rather than fully detailing every cable and attachment at all times, the system models only the necessary portions, maintaining computational efficiency while achieving sufficient collision detection accuracy for safe operation.
Solution Approach 2:
The digital representation transitions from static to dynamic, allowing the model to adapt its level of detail based on real-time robot configuration and operational context. When cables are in positions that could cause collisions, they are included in the digital representation; when they are in safe positions, they can be excluded or simplified, maintaining speed while preserving accuracy when needed.
3Reliability
If the robot filters out only its main body from the operational environment model, then processing is simpler, but path planning accuracy deteriorates because the robot may collide with its own cables or attached structures
Solution Approach 1:
The filtering process is segmented to handle different robot components separately. The main body filtering continues to operate as before, while an additional filtering layer specifically handles attached structures like cables. This segmentation allows the system to maintain the simplicity of main body filtering while adding targeted complexity only where needed for cable and attachment safety.
Solution Approach 2:
The patent introduces an intermediary digital representation layer that sits between the physical robot and the operational environment model. This intermediary representation specifically captures the positions and configurations of cables and attached structures, acting as a mediator that provides collision information without requiring direct complex modeling of every physical component in the main filtering process.
Data Source
AI summary
An oversized representation of at least a portion of a robot is filtered (e.g., voxels are set as unoccupied for any objects that reside completely within the oversized representation) from a representation of an operational environment, which provides a digital model of the operational environment which can, for example, be used for motion planning for the robot. The oversized representation exceeds a physical dimension of at least a portion (e.g. appendage) of the robot, to advantageously account for cables and other features that are attached to, and extending beyond, the outer dimensions of the robot. The specific dimensions of the oversized representation can be based on a variety of factors, for example a geometry of the cable, orientation or position of the robot appendage, orientation or position of the cable with respect to the robot appendage, velocity of the appendage, slack in the cable, etc., which may be modeled.