no code implementations • 8 Nov 2024 • Puze Liu, Jonas Günster, Niklas Funk, Simon Gröger, Dong Chen, Haitham Bou-Ammar, Julius Jankowski, Ante Marić, Sylvain Calinon, Andrej Orsula, Miguel Olivares-Mendez, Hongyi Zhou, Rudolf Lioutikov, Gerhard Neumann, Amarildo Likmeta Amirhossein Zhalehmehrabi, Thomas Bonenfant, Marcello Restelli, Davide Tateo, Ziyuan Liu, Jan Peters
Despite the many challenges associated with combining machine learning technology with robotics, robot learning remains one of the most promising directions for enhancing the capabilities of robots.
1 code implementation • 18 Sep 2024 • Jonas Günster, Puze Liu, Jan Peters, Davide Tateo
Safety is one of the key issues preventing the deployment of reinforcement learning techniques in real-world robots.
1 code implementation • 10 Sep 2024 • Nico Bohlinger, Grzegorz Czechmanowski, Maciej Krupka, Piotr Kicki, Krzysztof Walas, Jan Peters, Davide Tateo
Our experiments show that URMA can learn a locomotion policy on multiple embodiments that can be easily transferred to unseen robot platforms in simulation and the real world.
no code implementations • 6 Sep 2024 • Felix Herrmann, Sebastian Zach, Jacopo Banfi, Jan Peters, Georgia Chalvatzaki, Davide Tateo
Estimating collision probabilities between robots and environmental obstacles or other moving agents is crucial to ensure safety during path planning.
no code implementations • 26 Aug 2024 • Piotr Kicki, Davide Tateo, Puze Liu, Jonas Guenster, Jan Peters, Krzysztof Walas
We evaluate our approach against state-of-the-art safe reinforcement learning methods, showing that our technique, particularly when exploiting task structure, outperforms baseline methods in challenging scenarios such as planning to hit in robot air hockey.
1 code implementation • 16 Jul 2024 • Henri-Jacques Geiß, Firas Al-Hafez, Andre Seyfarth, Jan Peters, Davide Tateo
Learning a locomotion controller for a musculoskeletal system is challenging due to over-actuation and high-dimensional action space.
1 code implementation • 28 Jun 2024 • Christopher E. Mower, Yuhui Wan, Hongzhan Yu, Antoine Grosnit, Jonas Gonzalez-Billandon, Matthieu Zimmer, Jinlong Wang, Xinyu Zhang, Yao Zhao, Anbang Zhai, Puze Liu, Daniel Palenicek, Davide Tateo, Cesar Cadena, Marco Hutter, Jan Peters, Guangjian Tian, Yuzheng Zhuang, Kun Shao, Xingyue Quan, Jianye Hao, Jun Wang, Haitham Bou-Ammar
Key features of the framework include: integration of ROS with an AI agent connected to a plethora of open-source and commercial LLMs, automatic extraction of a behavior from the LLM output and execution of ROS actions/services, support for three behavior modes (sequence, behavior tree, state machine), imitation learning for adding new robot actions to the library of possible actions, and LLM reflection via human and environment feedback.
no code implementations • 13 Apr 2024 • Puze Liu, Haitham Bou-Ammar, Jan Peters, Davide Tateo
Indeed, safety specifications, often represented as constraints, can be complex and non-linear, making safety challenging to guarantee in learning systems.
1 code implementation • ICLR 2020 • Carlo D'Eramo, Davide Tateo, Andrea Bonarini, Marcello Restelli, Jan Peters
We study the benefit of sharing representations among tasks to enable the effective use of deep neural networks in Multi-Task Reinforcement Learning.
no code implementations • 13 Nov 2023 • Luca Lach, Robert Haschke, Davide Tateo, Jan Peters, Helge Ritter, Júlia Borràs, Carme Torras
The advent of tactile sensors in robotics has sparked many ideas on how robots can leverage direct contact measurements of their environment interactions to improve manipulation tasks.
no code implementations • 7 Nov 2023 • Firas Al-Hafez, Guoping Zhao, Jan Peters, Davide Tateo
Stateful policies play an important role in reinforcement learning, such as handling partially observable environments, enhancing robustness, or imposing an inductive bias directly into the policy structure.
2 code implementations • 4 Nov 2023 • Firas Al-Hafez, Guoping Zhao, Jan Peters, Davide Tateo
Imitation Learning (IL) holds great promise for enabling agile locomotion in embodied agents.
1 code implementation • 1 Mar 2023 • Firas Al-Hafez, Davide Tateo, Oleg Arenz, Guoping Zhao, Jan Peters
Recent methods for imitation learning directly learn a $Q$-function using an implicit reward formulation rather than an explicit reward function.
1 code implementation • 11 Jan 2023 • Piotr Kicki, Puze Liu, Davide Tateo, Haitham Bou-Ammar, Krzysztof Walas, Piotr Skrzypczyński, Jan Peters
Motion planning is a mature area of research in robotics with many well-established methods based on optimization or sampling the state space, suitable for solving kinematic motion planning.
no code implementations • 27 Sep 2022 • Puze Liu, Kuo Zhang, Davide Tateo, Snehal Jauhri, Zhiyuan Hu, Jan Peters, Georgia Chalvatzaki
Our proposed approach achieves state-of-the-art performance in simulated high-dimensional and dynamic tasks while avoiding collisions with the environment.
1 code implementation • 21 Jun 2022 • Davide Tateo, Davide Antonio Cucci, Matteo Matteucci, Andrea Bonarini
In this paper, we propose the use of an efficient representation, based on structural points, for the geometry of objects to be used as landmarks in a monocular semantic SLAM system based on the pose-graph formulation.
no code implementations • 9 Mar 2022 • Marius Memmel, Puze Liu, Davide Tateo, Jan Peters
Black-box policy optimization is a class of reinforcement learning algorithms that explores and updates the policies at the parameter level.
no code implementations • 9 Mar 2022 • Puze Liu, Kuo Zhang, Davide Tateo, Snehal Jauhri, Jan Peters, Georgia Chalvatzaki
Autonomous robots should operate in real-world dynamic environments and collaborate with humans in tight spaces.
no code implementations • 22 Oct 2021 • Julen Urain, Davide Tateo, Jan Peters
Learning robot motions from demonstration requires models able to specify vector fields for the full robot pose when the task is defined in operational space.
1 code implementation • 20 Jul 2021 • João Carvalho, Davide Tateo, Fabio Muratore, Jan Peters
This estimator is unbiased, has low variance, and can be used with differentiable and non-differentiable function approximators.
no code implementations • 11 Dec 2020 • Julen Urain, Davide Tateo, Tianyu Ren, Jan Peters
We present a new family of deep neural network-based dynamic systems.
no code implementations • 25 Oct 2020 • Julen Urain, Michelle Ginesi, Davide Tateo, Jan Peters
We introduce ImitationFlow, a novel Deep generative model that allows learning complex globally stable, stochastic, nonlinear dynamics.
1 code implementation • 10 Jun 2020 • Riad Akrour, Davide Tateo, Jan Peters
Reinforcement learning (RL) has demonstrated its ability to solve high dimensional tasks by leveraging non-linear function approximators.
2 code implementations • 4 Jan 2020 • Carlo D'Eramo, Davide Tateo, Andrea Bonarini, Marcello Restelli, Jan Peters
MushroomRL is an open-source Python library developed to simplify the process of implementing and running Reinforcement Learning (RL) experiments.
1 code implementation • 1 Jan 2020 • Simone Parisi, Davide Tateo, Maximilian Hensel, Carlo D'Eramo, Jan Peters, Joni Pajarinen
Empirical results on classic and novel benchmarks show that the proposed approach outperforms existing methods in environments with sparse rewards, especially in the presence of rewards that create suboptimal modes of the objective function.