About
17
Publications
2,512
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
201
Citations
Introduction
Skills and Expertise
Current institution
Additional affiliations
May 2021 - August 2024
Education
October 2014 - September 2016
Publications
Publications (17)
Recent advances in deep neural networks have opened up new possibilities for visuomotor robot learning. In the context of human-robot or robot-robot collaboration, such networks can be trained to predict future poses and this information can be used to improve the dynamics of cooperative tasks. This is important, both in terms of realizing various...
Autonomous robot learning in unstructured environments often faces the problem that the dimensionality of the search space is too large for practical applications. Dimensionality reduction techniques have been developed to address this problem and describe motor skills in low-dimensional latent spaces. Most of these techniques require the availabil...
Just like humans, robots can improve their performance by practicing, i. e. by performing the desired behavior many times and updating the underlying skill representation using the newly gathered data. In this paper, we propose to implement robot practicing by applying statistical and reinforcement learning (RL) in a latent space of the selected sk...
Modern factories and factories of the future are increasing their demands in terms of productivity and time of production line adaptation for the each new product. Products from automated production lines are often checked with machine vision, but the process of inspection is setup manually. Manually setup processes are not optimal so they represen...
In order to increase the autonomy of the modern, high complexity robots with multiple degrees of freedom, it is necessary for them to be able to learn and adapt their skills, for example, using reinforcement learning (RL). However, RL performance greatly depends on the task dimensionality. Methods for reducing the task dimensionality, such as deep...
Dynamic movement primitives (DMPs) have proven to be an effective movement representation for motor skill learning. In this paper, we propose a new approach for training deep neural networks to synthesize dynamic movement primitives. The distinguishing property of our approach is that it can utilize a novel loss function that measures the physical...
Autonomous learning and adaptation of robotic trajectories by complex robots in unstructured environments, for example with the use of reinforcement learning, very quickly encounters problems where the dimensionality of the search space is beyond the range of practical use. Different methods of reducing the dimensionality have been proposed in the...
A deep encoder-decoder network was previously proposed for learning a mapping from raw images to dynamic movement primitives in order to enable a robot to draw sketches of numeric digits when shown images of same. In this paper, the network architecture, which was previously constructed entirely with fully-connected linear layers, is modified to in...
The choice of an appropriate representation is important when reconstructing motion from images. In this letter we propose a new type of deep neural network (DNN) that maps images to spatial paths represented by a recently introduced motion representation called arc-length dynamic movement primitive (AL-DMP). This representation separates the spati...
Autonomous learning is critical for the future where the robots should operate in unstructured environments. Reinforcement learning is one of the main approaches for learning in contemporary robotics. With the rise of neu-ral networks in recent studies, the idea of incorporating neural networks with classic Q-learning algorithm for learning policie...
Reinforcement learning refers to powerful algorithms for solving goal related problems by maximizing the reward over many time steps. By incorporating them into the dynamic movement primitives (DMPs) which are now widely used parametric representations in robotics, movements obtained from a single human demonstration can be adapted so that a robot...
