Autonomous Robot Pose Determination for Flexible Object Handling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomous robots struggle to adapt to unexpected changes in their environment, requiring precise knowledge of object locations and loading processes, leading to inefficiencies and manual intervention when objects are not exactly where expected.
Innovation Solution
A system that uses a 3D map updated in real-time by a central communication system and robots, allowing robots to identify objects and determine their pose without needing micro-level precision, enabling autonomous operation and flexibility in unloading tasks without prior knowledge of loading processes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If robots use micro-level precision (1-2 cm) to locate objects, then object identification accuracy is improved, but system adaptability deteriorates when objects shift positions
Solution Approach 1:
The system dynamically adjusts the precision requirement from micro-level (1-2 cm) to macro-level (half object dimension) based on the task context. The robot uses vision systems to identify objects at macro-level precision, then uses grippers with compliance control to adapt to the actual object position and orientation, eliminating the need for micro-level positioning precision while maintaining task completion capability.
Solution Approach 2:
The patent changes the precision parameter from 1-2 cm to half the object dimension (e.g., 40 cm for an 80 cm wide pallet). This parameter change is supported by combining vision-based macro-level localization with compliant gripper control, allowing the system to work with reduced precision requirements while maintaining effectiveness.
2Reliability
If robots require exact knowledge of loading processes, then task execution reliability is improved, but system complexity deteriorates
Solution Approach 1:
The robot performs self-calibration by approaching the object and using its vision system to automatically identify the object's actual position, orientation, and dimensions. The compliant gripper automatically adapts to the object's characteristics during approach and contact. This self-service capability eliminates the need for external systems to provide detailed loading process information, reducing system complexity while maintaining reliability.
Solution Approach 2:
The system uses vision feedback to detect the object's actual state and adjusts the gripper's approach and grasping force accordingly. This closed-loop feedback mechanism allows the robot to adapt to unknown loading configurations without requiring prior knowledge, maintaining reliability while avoiding the complexity of pre-programming all possible loading scenarios.
3Productivity
If robots expend fuel attempting failed tasks, then productivity deteriorates, but measurement precision requirements worsen
Solution Approach 1:
The system performs partial action by using vision systems to identify objects at macro-level precision (half object dimension) rather than requiring full micro-level precision (1-2 cm). This partial precision approach is sufficient for successful task completion when combined with compliant gripper control, preventing wasted fuel on failed attempts while reducing precision requirements.
Data Source
AI summary
A system and a method are disclosed where an autonomous robot captures an image of an object to be transported from a source to a destination. The robot generates a bounding box within the image surrounding the object. The robot applies a machine-learned model to the image with the bounding box, the machine-learned model configured to identify an object type of the object, and to identify features of the object based on the identified object type and the image. The robot determines which of the identified features of the object are visible to the autonomous robot, and determines a three-dimensional pose of the object based on the features determined to be visible to the autonomous robot.