Hasil untuk "cs.RO"

Andrei Costinescu, Darius Burschka

This paper presents a framework to define a task with freedom and variability in its goal state. A robot could use this to observe the execution of a task and target a different goal from the observed one; a goal that is still compatible with the task description but would be easier for the robot to execute. We define the model of an environment state and an environment variation, and present experiments on how to interactively create the variation from a single task demonstration and how to use this variation to create an execution plan for bringing any environment into the goal state.

Emily Jensen, Sriram Sankaranarayanan, Bradley Hayes

We claim that LLMs can be paired with formal analysis methods to provide accessible, relevant feedback for HRI tasks. While logic specifications are useful for defining and assessing a task, these representations are not easily interpreted by non-experts. Luckily, LLMs are adept at generating easy-to-understand text that explains difficult concepts. By integrating task assessment outcomes and other contextual information into an LLM prompt, we can effectively synthesize a useful set of recommendations for the learner to improve their performance.

Adarsh Srivastava

Offline planning often struggles with poor sampling efficiency as it tries to learn policies from scratch. Especially with diffusion models, such cold start practices mean that both training and sampling become very expensive. We hypothesize that certain environment constraint priors or cheaply available policies make it unnecessary to learn from scratch, and explore a way to incorporate such priors in the learning process. To achieve that, we borrow a variation of the Schrödinger bridge formulation from the image-to-image setting and apply it to planning tasks. We study the performance on some planning tasks and compare the performance against the DDPM formulation. The code for this work is available at https://github.com/adrshsrvstv/bridge_diffusion_planning.

William Thibault, Vidyasagar Rajendran, William Melek et al.

Learning-based methods have proven useful at generating complex motions for robots, including humanoids. Reinforcement learning (RL) has been used to learn locomotion policies, some of which leverage a periodic reward formulation. This work extends the periodic reward formulation of locomotion to skateboarding for the REEM-C robot. Brax/MJX is used to implement the RL problem to achieve fast training. Initial results in simulation are presented with hardware experiments in progress.

Arunabh Bora

The field of warehouse robotics is currently in high demand, with major technology and logistics companies making significant investments in these advanced systems. Training robots to operate in such complex environments is challenging, often requiring human supervision for adaptation and learning. Interactive reinforcement learning (IRL) is a key training methodology in human-computer interaction. This paper presents a comparative study of two IRL algorithms: Q-learning and SARSA, both trained in a virtual grid-simulation-based warehouse environment. To maintain consistent feedback rewards and avoid bias, feedback was provided by the same individual throughout the study.

Junlin Song, Antoine Richard, Miguel Olivares-Mendez

Accurate disturbance estimation is crucial for reliable robotic physical interaction. To estimate environmental interference in a low-cost and sensorless way (without force sensor), a variety of tightly-coupled visual inertial external force estimators are proposed in the literature. However, existing solutions may suffer from relatively low-frequency preintegration. In this paper, a novel estimator is designed to overcome this issue via high-frequency instantaneous accelerometer update.

Antonio Losada González

This work presents a three-dimensional geometric resolution method to calculate the complete inverse kinematics of a 7-degree-of-freedom articulated arm, including the hand itself. The method is classified as an analytical method with geometric solution, since it obtains a precise solution in a closed number of steps, converting the inverse kinematic problem into a three-dimensional geometric model. To simplify the problem, the kinematic decoupling method is used, so that the position of the wrist is calculated independently on one hand with information on the orientation of the hand, and the angles of the rest of the arm are calculated from the wrist.

Antonio Losada González

SAPPO is a high-precision, low-cost and highly scalable indoor localization system. The system is designed using modified HC-SR04 ultrasound transducers as a base to be used as distance meters between beacons and mobile robots. Additionally, it has a very unusual arrangement of its elements, such that the beacons and the array of transmitters of the mobile robot are located in very close planes, in a horizontal emission arrangement, parallel to the ground, achieving a range per transducer of almost 12 meters. SAPPO represents a significant leap forward in ultrasound localization systems, in terms of reducing the density of beacons while maintaining average precision in the millimeter range.

Ilkwon Hong, Junhyoung Ha

In this study, we rediscovered the framework of generative adversarial networks (GANs) as a solver for calibration problems without data correspondence. When data correspondence is not present or loosely established, the calibration problem becomes a parameter estimation problem that aligns the two data distributions. This procedure is conceptually identical to the underlying principle of GAN training in which networks are trained to match the generative distribution to the real data distribution. As a primary application, this idea is applied to the hand-eye calibration problem, demonstrating the proposed method's applicability and benefits in complicated calibration problems.

Michael M. Bilevich, Shahar Guini, Dan Halperin

We present a method for determining the unknown location of a sensor placed in a known 2D environment in the presence of unknown dynamic obstacles, using only few distance measurements. We present guarantees on the quality of the localization, which are robust under mild assumptions on the density of the unknown/dynamic obstacles in the known environment. We demonstrate the effectiveness of our method in simulated experiments for different environments and varying dynamic-obstacle density. Our open source software is available at https://github.com/TAU-CGL/vb-fdml2-public.

Jhair S. Gallego, Ricardo E. Ramirez

This work describes the process of integrating a depth camera into the navigation system of a self-driving ground vehicle (SDV) and the implementation of a multilayer costmap that enhances the vehicle's obstacle identification process by expanding its two-dimensional field of view, based on 2D LIDAR, to a three-dimensional perception system using an RGB-D camera. This approach lays the foundation for a robust vision-based navigation and obstacle detection system. A theoretical review is presented and implementation results are discussed for future work.

Ananda Rangan Narayanan, Mi Zhou, Erik Verriest

In this article, we consider the path-planning problem of a cooperative homogeneous robotic system with rigid formation. An optimal controller is designed for each agent in such rigid systems based on Pontryagin's minimum principle theory. We found that the optimal control for each agent is equivalent to the optimal control for the Center of Mass (CoM). This equivalence is then proved by using some analytical mechanics. Three examples are finally simulated to illustrate our theoretical results. One application could be utilizing this equivalence to simplify the original multi-agent optimal control problem.

Astrid Rosenthal-von der Pütten, Stefan Schiffer

This paper focuses on the identification of different algorithm-based biases in robotic behaviour and their consequences in human-robot mixed groups. We propose to develop computational models to detect episodes of microaggression, discrimination, and social exclusion informed by a) observing human coping behaviours that are used to regain social inclusion and b) using system inherent information that reveal unequal treatment of human interactants. Based on this information we can start to develop regulatory mechanisms to promote fairness and social inclusion in HRI.

Thomas Fork, Francesco Borrelli

We present two quadrotor raceline optimization approaches which differ in using Euclidean or non-Euclidean geometry to describe vehicle position. Both approaches use high-fidelity quadrotor dynamics and avoid the need to approximate gates using waypoints. We demonstrate both approaches on simulated racetracks with realistic vehicle parameters where we demonstrate 100x faster compute time than comparable published methods and improved solver convergence. We then extend the non-Euclidean approach to compute racelines in the presence of numerous static obstacles.

Kyriakos Papadopoulos, Apostolos Syropoulos

The motion planning problem is a fundamental problem in robotics, so that every autonomous robot should be able to deal with it. A number of solutions have been proposed and a probabilistic one seems to be quite reasonable. However, here we propose a more adoptive solution that uses fuzzy set theory and we expose this solution next to a sort survey on the recent theory of soft robots, for a future qualitative comparison between the two.

Emmanouil Tsardoulias, Pericles Mitkas

Nowadays, the construction of a complex robotic system requires a high level of specialization in a large number of diverse scientific areas. It is reasonable that a single researcher cannot create from scratch the entirety of this system, as it is impossible for him to have the necessary skills in the necessary fields. This obstacle is being surpassed with the existent robotic frameworks. This paper tries to give an extensive review of the most famous robotic frameworks and middleware, as well as to provide the means to effortlessly compare them. Additionally, we try to investigate the differences between the definitions of a robotic framework, a robotic middleware and a robotic architecture.

Joan Solà

This article is an exhaustive revision of concepts and formulas related to quaternions and rotations in 3D space, and their proper use in estimation engines such as the error-state Kalman filter. The paper includes an in-depth study of the rotation group and its Lie structure, with formulations using both quaternions and rotation matrices. It makes special attention in the definition of rotation perturbations, derivatives and integrals. It provides numerous intuitions and geometrical interpretations to help the reader grasp the inner mechanisms of 3D rotation. The whole material is used to devise precise formulations for error-state Kalman filters suited for real applications using integration of signals from an inertial measurement unit (IMU).

Anatoly Pashkevich, Alexandr Klimchik, Stéphane Caro et al.

The paper focuses on stiffness matrix computation for manipulators with passive joints. It proposes both explicit analytical expressions and an efficient recursive procedure that are applicable in general case and allow obtaining the desired matrix either in analytical or numerical form. Advantages of the developed technique and its ability to produce both singular and non-singular stiffness matrices are illustrated by application examples that deal with stiffness modeling of two Stewart-Gough platforms.

Damien Chablat, Philippe Wenger

The aim of this paper is to characterize the moveability of fully-parallel manipulators in the presence of obstacles. Fully parallel manipulators are used in applications where accuracy, stiffness or high speeds and accelerations are required \cite{Merlet:97}. However, one of its main drawbacks is a relatively small workspace compared to the one of serial manipulators. This is due mainly to the existence of potential internal collisions, and the existence of singularities. In this paper, the notion of free aspect is defined which permits to exhibit domains of the workspace and the joint space free of singularity and collision. The main application of this study is the moveability analysis in the workspace of the manipulator as well as path-planning, control and design.

Alex Ellery

In this second of three short papers, I introduce some of the basic concepts of space robotics with an emphasis on some specific challenging areas of research that are peculiar to the application of robotics to space infrastructure development. The style of these short papers is pedagogical and the concepts in this paper are developed from fundamental manipulator robotics. This second paper considers the application of space manipulators to on-orbit servicing (OOS), an application which has considerable commercial application. I provide some background to the notion of robotic on-orbit servicing and explore how manipulator control algorithms may be modified to accommodate space manipulators which operate in the micro-gravity of space.