AI-Driven Visual Navigation for Smart Lab Tour Guide Robot
Bibliographic record
Abstract
A self-contained guidance system is required in robotics and automation laboratories for autonomous navigation purposes.In laboratory conditions where conditions are constantly changing, regular fixed-path solutions will not work.In this paper, a comprehensive framework for a tour guide robot is developed.An AI-driven visual navigation system is used to guide the robot.Simultaneous localization and mapping (SLAM) is implemented instead of the traditional line following approach.Deep learning-based obstacle detection is optimized for robot path planning.ORB-SLAM2 (monocular version) is considered for real-time localization and mapping.A specific data set is taken from the laboratory for fine-tuning of YOLOv5s for dynamic obstacle detection.The algorithm is extended for real-time path planning to avoid obstacles in the robot's path.Raspberry Pi 4 and Arduino Uno are used for the development of the embedded system so that it compares both for practical deployment feasibility.In this research, a 40% reduction in tour completion time and a 95% obstacle avoidance success rate are achieved.This investigation has achieved an average path deviation accuracy of 1.1 cm.A sensor fusion architecture is used to combine visual SLAM feature with deep learning detection for robust navigation.This research considers and impacts the architecture contrasts on hardware.Extensive performance characteristics are studied under different environmental conditions.This proposed AI-driven robot navigation in lab operations has set a new benchmark for intelligent robotics in academia and the public sector.
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 | 0.003 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.002 | 0.000 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.003 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| 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".