Krzysztof Ciebiera

Piotr Krzywicki, Krzysztof Ciebiera, Rafał Michaluk et al.

Gathering real-world data from the robot quickly becomes a bottleneck when constructing a robot learning system for grasping. In this work, we design a semi-supervised grasping system that, on top of a small sample of robot experience, takes advantage of images of products to be picked, which are collected without any interactions with the robot. We validate our findings both in the simulation and in the real world. In the regime of a small number of robot training samples, taking advantage of the unlabeled data allows us to achieve performance at the level of 10-fold bigger dataset size used by the baseline. The code and datasets used in the paper will be released at https://github.com/nomagiclab/grasping-student.

Kevin Qiu, Władysław Pałucki, Krzysztof Ciebiera et al.

We introduce RoboMorph, an automated approach for generating and optimizing modular robot designs using large language models (LLMs) and evolutionary algorithms. In this framework, we represent each robot design as a grammar and leverage the capabilities of LLMs to navigate the extensive robot design space, which is traditionally time-consuming and computationally demanding. By introducing a best-shot prompting technique and a reinforcement learning-based control algorithm, RoboMorph iteratively improves robot designs through feedback loops. Experimental results demonstrate that RoboMorph successfully generates nontrivial robots optimized for different terrains while showcasing improvements in robot morphology over successive evolutions. Our approach highlights the potential of using LLMs for data-driven, modular robot design, providing a promising methodology that can be extended to other domains with similar design frameworks.

Władysław Pałucki, Paweł Siwak, Krzysztof Ciebiera et al.

The recent popularity of robotics, combined with the steadily decreasing cost of robotic hardware, has lowered the entry barrier to robotics research and enabled rapid advancements in the field. One of the primary examples is the Unitree Go2 quadruped robot, which is often used by researchers in the areas of locomotion, navigation, control, and others. Many researchers use the Go2 robot in combination with techniques like imitation learning, reinforcement learning, and behavioral cloning to allow machine learning systems to take full control of the robot. At the same time, many of those techniques require demonstration data consisting of the robot's kinematics information and actions applied to the motors. Obtaining such data is difficult, requires building complex pipelines, and can take significant time. To aid in those kinds of efforts, we present Kine2Go - a dataset with 800 diverse gait kinematics trajectory motion data for the Unitree Go2 robot, derived from 40 distinct policies. Our pipeline accepts data from various quadruped morphologies and translates them to a Go2-compatible format. Then we use Reinforcement Learning to train policies following a given motion, and finally we gather data from those policies, which grants robust, perturbed kinematic data with corresponding motor-level actions.

Krzysztof Ciebiera, Piotr Godlewski, Piotr Sankowski et al.

This paper summarizes the work on implementing few solutions for the Steiner Tree problem which we undertook in the PAAL project. The main focus of the project is the development of generic implementations of approximation algorithms together with universal solution frameworks. In particular, we have implemented Zelikovsky 11/6-approximation using local search framework, and 1.39-approximation by Byrka et al. using iterative rounding framework. These two algorithms are experimentally compared with greedy 2-approximation, with exact but exponential time Dreyfus-Wagner algorithm, as well as with results given by a state-of-the-art local search techniques by Uchoa and Werneck. The results of this paper are twofold. On one hand, we demonstrate that high level algorithmic concepts can be designed and efficiently used in C++. On the other hand, we show that the above algorithms with good theoretical guarantees, give decent results in practice, but are inferior to state-of-the-art heuristical approaches.