arXiv subjects

Tadej Petrič

Publications and source records attributed to Tadej Petrič.

5 recordsLinked to original sources

arXiv2025

A Survey on Imitation Learning for Contact-Rich Tasks in Robotics

This paper comprehensively surveys research trends in imitation learning for contact-rich robotic tasks. Contact-rich tasks, which require complex physical interactions with the environment, represent a central challenge in robotics due to their nonlinear dynamics and sensitivity to small positional deviations. The paper examines demonstration collection methodologies, including teaching methods and sensory modalities crucial for capturing subtle interaction dynamics. We then analyze imitation learning approaches, highlighting their applications to contact-rich manipulation. Recent advances in multimodal learning and foundation models have significantly enhanced performance in complex contact tasks across industrial, household, and healthcare domains. Through systematic organization of current research and identification of challenges, this survey provides a foundation for future advancements in contact-rich robotic manipulation.

cs.RO↗

arXiv2023

The JSI-KneExo: Active, Quasi-Passive, Pneumatic, Portable Knee Exo with Bidirectional Energy Flow for Air Recovery in Sit-Stand Tasks

While existing literature encompasses exoskeleton-assisted sit-stand tasks, the integration of energy recovery mechanisms remains unexplored. To push these boundaries further, this study introduces a portable pneumatic knee exoskeleton that operates in both quasi-passive and active modes, where active mode is utilized for aiding in standing up (power generation), thus the energy flows from the exoskeleton to the user, and quasi-passive mode for aiding in sitting down (power absorption), where the device absorbs and can store energy in the form of compressed air, leading to energy savings in active mode. The absorbed energy can be stored and later reused without compromising exoskeleton transparency in the meantime. In active mode, a small air pump inflates the pneumatic artificial muscle (PAM), which stores the compressed air, that can then be released into a pneumatic cylinder to generate torque. All electronic and pneumatic components are integrated into the system, and the exoskeleton weighs 3.9 kg with a maximum torque of 20 Nm at the knee joint. The paper describes the mechatronic design, mathematical model and includes a pilot study with an able-bodied subject performing sit-to-stand tasks. The results show that the exoskeleton can recover energy while assisting the subject and reducing muscle activity. Furthermore, results underscore air regeneration's impact on energy-saving in portable pneumatic exoskeletons.

cs.RO↗

arXiv2023

Learning Joint Space Reference Manifold for Reliable Physical Assistance

This paper presents a study on the use of the Talos humanoid robot for performing assistive sit-to-stand or stand-to-sit tasks. In such tasks, the human exerts a large amount of force (100--200 N) within a very short time (2--8 s), posing significant challenges in terms of human unpredictability and robot stability control. To address these challenges, we propose an approach for finding a spatial reference for the robot, which allows the robot to move according to the force exerted by the human and control its stability during the task. Specifically, we focus on the problem of finding a 1D manifold for the robot, while assuming a simple controller to guide its movement on this manifold. To achieve this, we use a functional representation to parameterize the manifold and solve an optimization problem that takes into account the robot's stability and the unpredictability of human behavior. We demonstrate the effectiveness of our approach through simulations and experiments with the Talos robot, showing robustness and adaptability.

cs.RO↗

arXiv2022

Leader-Follower Dynamics in Complex Obstacle Avoidance Task

A question that many researchers in social robotics are addressing is how to create more human-like behaviour in robots to make the collaboration between a human and a robot more intuitive to the human partner. In order to develop a human-like collaborative robotic system, however, human collaboration must first be better understood. Human collaboration is something we are all familiar with, however not that much is known about it from a kinematic standpoint. One dynamic that hasn't been researched thoroughly, yet naturally occurs in human collaboration, is for instance leader-follower dynamics. In our previous study, we tackled the question of leader-follower role allocation in human dyads during a collaborative reaching task, where the results implied that the subjects who performed higher in the individual experiment would naturally assume the role of a leader when in physical collaboration. In this study, we build upon the leader-follower role allocation study in human dyads by observing how the leader-follower dynamics change when the collaborative task becomes more complex. Here, the study was performed on a reaching task, where one subject in a dyad was faced with an additional task of obstacle avoidance when performing a 2D reaching task, while their partner was not aware of the obstacle. We have found that subjects change their roles throughout the task in order to complete it successfully, however looking at the overall task leader the higher-performing individual will always dominate over the lower-performing one, regardless of whether they are aware of the additional task of obstacle avoidance or not.

cs.RO↗

arXiv2022

Increased Complexity of a Human-Robot Collaborative Task May Increase the Need for a Socially Competent Robot

An important factor in developing control models for human-robot collaboration is how acceptable they are to their human partners. One such method for creating acceptable control models is to attempt to mimic human-like behaviour in robots so that their actions appear more intuitive to humans. To investigate how task complexity affects human perception and acceptance of their robot partner, we propose a novel human-based robot control model for obstacle avoidance that can account for the leader-follower dynamics that normally occur in human collaboration. The performance and acceptance of the proposed control method were evaluated using an obstacle avoidance scenario in which we compared task performance between individual tasks and collaborative tasks with different leader-follower dynamics roles for the robotic partner. The evaluation results showed that the robot control method is able to replicate human behaviour to improve the overall task performance of the subject in collaboration. However, regarding the acceptance of the robotic partner, the participants' opinions were mixed. Compared to the results of a study with a similar control method developed for a less complex task, the new results show a lower acceptance of the proposed control model, even though the control method was adapted to the more complex task from a dynamic standpoint. This suggests that the complexity of the collaborative task at hand increases the need not only for a more complex control model but also a more socially competent control model.

cs.RO↗