University of Twente Student Theses
Enhancing socially aware navigation of robots in healthcare environments through predicting human trajectories
Mytaros, Efstratios (2024) Enhancing socially aware navigation of robots in healthcare environments through predicting human trajectories.
|
PDF
11MB |
| Abstract: | This research explores the development and evaluation of a GRU-based trajectory prediction model aimed at forecasting human walking paths in enclosed spaces, such as hospitals. Utilizing datasets THOR and MAGNI, the study involved meticulous preprocessing steps, including the transformation of Cartesian coordinates to polar coordinates and handling missing values. The model’s performance was assessed using key metrics like Root Mean Squared Error (RMSE) and Euclidean distance, with a focus on both positional and angular accuracies. Results indicated that while the model performs well in familiar environments, it struggles with generalization to unseen scenarios. The study also highlights the need for more diverse training data and real-world validation to enhance model robustness. Future steps include refining preprocessing techniques, optimizing computational efficiency, and integrating multimodal data to improve trajectory prediction accuracy in dynamic indoor environments.. |
| Item Type: | Essay (Master) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 54 computer science |
| Programme: | Interaction Technology MSc (60030) |
| Link to this item: | https://purl.utwente.nl/essays/104184 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page