Task Based Pose Optimization of Modular Mobile Manipulators
Bibliographic record
Abstract
We propose a task based pose optimization method for modular mobile manipulators. The modular mobile manipulators are designed and prototyped by researchers at University of Waterloo. The intended application of the modular mobile manipulator is to assist urban search and rescue in unstructured environments. A single mobile manipulator with limited capability cannot achieve complex tasks in this application. When several modular mobile manipulators are linked to one another, they can perform complex tasks through decentralized collaboration. The focus of this research is to develop and simulate a task based pose optimization algorithm for several mobile robots linked by dexterous arms. A genetic algorithm is a bio-inspired optimization technique that mimics the process of evolution. In nature, many living organisms, such as ants and birds use genetic algorithms to forge for food and achieve complex tasks. The advantages of the genetic algorithm are its simplicity and effectiveness. The proposed genetic algorithm in this research optimizes the manipulability measure of the onboard mechanical manipulator arms. To verify the proposed task based pose optimization algorithm, a formation of three mobile manipulators serially connected through their onboard mechanical manipulators is considered in this research. The control architecture is organized into a three level hierarchy. On the top level, a human operator sends guiding commands to the lead module in the formation through a wireless communication channel. The median level control aims at optimizing the manipulator pose. The base level control is established with the input-output linearization. To add realistic considerations into the simulation environment, fractal terrains are generated with the popular Diamond-Square algorithm. The inclination angle of each mobile manipulator on the terrain is estimated through a four-point terrain-matching algorithm. The simulation is completed in MATLAB. Repetitive simulations are pursued in this research to confirm the simplicity and effectiveness of our approach to control machines that interact with the natural environment. The simulation program established in this research serves as a test environment for the task based pose optimization of modular mobile manipulators. The major contributions of this research are the optimization algorithm and the novel hardware design for the specified tasks.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".