Active transfer learning with neural networks through human-robot interactions (TRAIN)
Human Factors, Ergonomics, Human-Machine Systems
Final Report Abstract
This project aimed to enhance autonomous robot capabilities across various environments, focusing on improving human-robot interactions (HRI). Given the complexity of manually programming diverse motor and manipulation skills, we explored Learning from Demonstration (LfD) for enabling self-improving robotic systems. LfD leverages human expertise through recorded sensor data, facilitating more intuitive and adaptive autonomous behaviors. A significant component of the project involved integrating Interactive Bayesian Optimization (IBO) to incorporate human feedback into reinforcement learning (RL) tasks, which enhanced the optimization of robotic trajectories. The Preference Expected Improvement (PEI) framework within IBO balanced user guidance and algorithmic learning, leading to more efficient skill acquisition. Additionally, we tackled the issue of posterior collapse in Variational Autoencoders (VAEs) by introducing a Contrastive Regularization (CR-VAE) approach, which greatly improved the quality of latent representations across various datasets. To understand user experiences (UX) and trust in HRI better, we examined how training data influences trust in RL agents. Results indicated that agents trained with expert human data were trusted significantly more than those with beginner data, emphasizing the importance of perceived human-like behavior in fostering user trust. Moreover, we developed a human-centered adaptive framework focusing on real-time trust assessment through physiological data. Key innovations included a sensor glove with enhanced capabilities and a Mixed Reality interface for intuitive visualization of robot actions. Findings revealed that emotional states, such as valence and arousal, directly impacted trust levels, reinforcing the necessity of adaptive autonomy to improve UX. The project demonstrated the potential of integrating UX in machine learning for reliable and intuitive interactions with robots. By enhancing user trust and HRI quality, we established a framework for effective robot deployment in collaborative environments, ensuring that robots can assist safely and efficiently in everyday tasks. The findings underscore the relevance of human guidance in optimizing robot learning processes and reliability.
Publications
-
Learning Hierarchical Acquisition Functions for Bayesian Optimization. 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 5490-5496. IEEE.
Rottmann, Nils; Kunavar, Tjasa; Babic, Jan; Peters, Jan & Rueckert, Elmar
-
Sample-Efficient Covariance Matrix Adaptation Evolutional Strategy via Simulated Rollouts in Neural Networks. International Conference on Advances in Signal Processing and Artificial Intelligence, 2020
Xue, H.; Boettger, S.; Rottmann, N.; Pandya, H.; Bruder, R.; Neumann, G.; Schweikard, A. & Rueckert, E.
-
A high-accuracy, low-budget Sensor Glove for Trajectory Model Learning. 2021 20th International Conference on Advanced Robotics (ICAR), 1109-1115. IEEE.
Denz, Robin; Demirci, Rabia; Cansev, M. Ege; Bliek, Adna; Beckerle, Philipp; Rueckert, Elmar & Rottmann, Nils
-
Interactive Human–Robot Skill Transfer: A Review of Learning Methods and User Experience. Advanced Intelligent Systems, 3(7).
Cansev, Mehmet Ege; Xue, Honghu; Rottmann, Nils; Bliek, Adna; Miller, Luke E.; Rueckert, Elmar & Beckerle, Philipp
-
Peripheral Neuroergonomics – An Elegant Way to Improve Human-Robot Interaction?. Frontiers in Neurorobotics, 15.
Del Vecchio, Alessandro; Castellini, Claudio & Beckerle, Philipp
-
Predictive Exoskeleton Control for Arm-Motion Augmentation Based on Probabilistic Movement Primitives Combined With a Flow Controller. IEEE Robotics and Automation Letters, 6(3), 4417-4424.
Jamsek, Marko; Kunavar, Tjasa; Bobek, Urban; Rueckert, Elmar & Babic, Jan
-
SKID RAW: Skill Discovery From Raw Trajectories. IEEE Robotics and Automation Letters, 6(3), 4696-4703.
Tanneberg, Daniel; Ploeger, Kai; Rueckert, Elmar & Peters, Jan
-
Can we infer the full-arm manipulation skills from tactile targets? Workshop at Humanoids, 2022
Dave, V. & Rueckert, E.
-
Predicting full-arm grasping motions from anticipated tactile responses. 2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids), 464-471. IEEE.
Dave, Vedant & Rueckert, Elmar
-
Using Deep Reinforcement Learning with Automatic Curriculum Learning for Mapless Navigation in Intralogistics. Applied Sciences, 12(6), 3153.
Xue, Honghu; Hein, Benedikt; Bakr, Mohamed; Schildbach, Georg; Abel, Bengt & Rueckert, Elmar
-
CR-VAE: Contrastive Regularization on Variational Autoencoders for Preventing Posterior Collapse. 2023 7th Asian Conference on Artificial Intelligence Technology (ACAIT), 427-437. IEEE.
Lygerakis, Fotios & Rueckert, Elmar
-
Advancing Interactive Robot Learning: A User Interface Leveraging Mixed Reality and Dual Quaternions. 2024 21st International Conference on Ubiquitous Robots (UR), 21-26. IEEE.
Feith, Nikolaus & Rueckert, Elmar
-
Integrating Human Expertise in Continuous Spaces: A Novel Interactive Bayesian Optimization Framework with Preference Expected Improvement. 2024 21st International Conference on Ubiquitous Robots (UR), 220-226. IEEE.
Feith, Nikolaus & Rueckert, Elmar
-
M2CURL: Sample-Efficient Multimodal Reinforcement Learning via Self-Supervised Representation Learning for Robotic Manipulation. 2024 21st International Conference on Ubiquitous Robots (UR), 490-497. IEEE.
Lygerakis, Fotios; Dave, Vedant & Rueckert, Elmar
-
Measuring, modeling and fostering embodiment of robotic prosthesis. Frontiers in Neuroergonomics, 5.
Bliek, Adna; Andreas, Daniel; Beckerle, Philipp & Rohe, Tim
-
Multimodal Visual-Tactile Representation Learning through Self-Supervised Contrastive Pre-Training. 2024 IEEE International Conference on Robotics and Automation (ICRA), 8013-8020. IEEE.
Dave, Vedant; Lygerakis, Fotios & Rueckert, Elmar
