arXiv subjects

Dimitrios Kanoulas

Publications and source records attributed to Dimitrios Kanoulas.

48 records · Page 3Linked to original sources

arXiv2023

ViT-A: Legged Robot Path Planning using Vision Transformer A

Legged robots, particularly quadrupeds, offer promising navigation capabilities, especially in scenarios requiring traversal over diverse terrains and obstacle avoidance. This paper addresses the challenge of enabling legged robots to navigate complex environments effectively through the integration of data-driven path-planning methods. We propose an approach that utilizes differentiable planners, allowing the learning of end-to-end global plans via a neural network for commanding quadruped robots. The approach leverages 2D maps and obstacle specifications as inputs to generate a global path. To enhance the functionality of the developed neural network-based path planner, we use Vision Transformers (ViT) for map pre-processing, to enable the effective handling of larger maps. Experimental evaluations on two real robotic quadrupeds (Boston Dynamics Spot and Unitree Go1) demonstrate the effectiveness and versatility of the proposed approach in generating reliable path plans.

cs.RO↗

arXiv2023

End-to-End Stable Imitation Learning via Autonomous Neural Dynamic Policies

State-of-the-art sensorimotor learning algorithms offer policies that can often produce unstable behaviors, damaging the robot and/or the environment. Traditional robot learning, on the contrary, relies on dynamical system-based policies that can be analyzed for stability/safety. Such policies, however, are neither flexible nor generic and usually work only with proprioceptive sensor states. In this work, we bridge the gap between generic neural network policies and dynamical system-based policies, and we introduce Autonomous Neural Dynamic Policies (ANDPs) that: (a) are based on autonomous dynamical systems, (b) always produce asymptotically stable behaviors, and (c) are more flexible than traditional stable dynamical system-based policies. ANDPs are fully differentiable, flexible generic-policies that can be used in imitation learning setups while ensuring asymptotic stability. In this paper, we explore the flexibility and capacity of ANDPs in several imitation learning tasks including experiments with image observations. The results show that ANDPs combine the benefits of both neural network-based and dynamical system-based methods.

cs.RO↗

arXiv2022

TeLeMan: Teleoperation for Legged Robot Loco-Manipulation using Wearable IMU-based Motion Capture

Human life is invaluable. When dangerous or life-threatening tasks need to be completed, robotic platforms could be ideal in replacing human operators. Such a task that we focus on in this work is the Explosive Ordnance Disposal. Robot telepresence has the potential to provide safety solutions, given that mobile robots have shown robust capabilities when operating in several environments. However, autonomy may be challenging and risky at this stage, compared to human operation. Teleoperation could be a compromise between full robot autonomy and human presence. In this paper, we present a relatively cheap solution for telepresence and robot teleoperation, to assist with Explosive Ordnance Disposal, using a legged manipulator (i.e., a legged quadruped robot, embedded with a manipulator and RGB-D sensing). We propose a novel system integration for the non-trivial problem of quadruped manipulator whole-body control. Our system is based on a wearable IMU-based motion capture system that is used for teleoperation and a VR headset for visual telepresence. We experimentally validate our method in real-world, for loco-manipulation tasks that require whole-body robot control and visual telepresence.

cs.RO↗

arXiv2022

One-Shot Transfer of Affordance Regions? AffCorrs!

In this work, we tackle one-shot visual search of object parts. Given a single reference image of an object with annotated affordance regions, we segment semantically corresponding parts within a target scene. We propose AffCorrs, an unsupervised model that combines the properties of pre-trained DINO-ViT's image descriptors and cyclic correspondences. We use AffCorrs to find corresponding affordances both for intra- and inter-class one-shot part segmentation. This task is more difficult than supervised alternatives, but enables future work such as learning affordances via imitation and assisted teleoperation.

cs.CV↗

arXiv2022

Robust Contact State Estimation in Humanoid Walking Gaits

In this article, we propose a deep learning framework that provides a unified approach to the problem of leg contact detection in humanoid robot walking gaits. Our formulation accomplishes to accurately and robustly estimate the contact state probability for each leg (i.e., stable or slip/no contact). The proposed framework employs solely proprioceptive sensing and although it relies on simulated ground-truth contact data for the classification process, we demonstrate that it generalizes across varying friction surfaces and different legged robotic platforms and, at the same time, is readily transferred from simulation to practice. The framework is quantitatively and qualitatively assessed in simulation via the use of ground-truth contact data and is contrasted against state of-the-art methods with an ATLAS, a NAO, and a TALOS humanoid robot. Furthermore, its efficacy is demonstrated in base estimation with a real TALOS humanoid. To reinforce further research endeavors, our implementation is offered as an open-source ROS/Python package, coined Legged Contact Detection (LCD).

cs.RO↗

arXiv2021

Improved Reinforcement Learning Coordinated Control of a Mobile Manipulator using Joint Clamping

Many robotic path planning problems are continuous, stochastic, and high-dimensional. The ability of a mobile manipulator to coordinate its base and manipulator in order to control its whole-body online is particularly challenging when self and environment collision avoidance is required. Reinforcement Learning techniques have the potential to solve such problems through their ability to generalise over environments. We study joint penalties and joint limits of a state-of-the-art mobile manipulator whole-body controller that uses LIDAR sensing for obstacle collision avoidance. We propose directions to improve the reinforcement learning method. Our agent achieves significantly higher success rates than the baseline in a goal-reaching environment and it can solve environments that require coordinated whole-body control which the baseline fails.

cs.RO↗

arXiv2021

Fully Self-Supervised Class Awareness in Dense Object Descriptors

We address the problem of inferring self-supervised dense semantic correspondences between objects in multi-object scenes. The method introduces learning of class-aware dense object descriptors by providing either unsupervised discrete labels or confidence in object similarities. We quantitatively and qualitatively show that the introduced method outperforms previous techniques with more robust pixel-to-pixel matches. An example robotic application is also shown~- grasping of objects in clutter based on corresponding points.

cs.RO↗

arXiv2020

Curved patch mapping and tracking for irregular terrain modeling: Application to bipedal robot foot placement

Legged robots need to make contact with irregular surfaces, when operating in unstructured natural terrains. Representing and perceiving these areas to reason about potential contact between a robot and its surrounding environment, is still largely an open problem. This paper introduces a new framework to model and map local rough terrain surfaces, for tasks such as bipedal robot foot placement. The system operates in real-time, on data from an RGB-D and an IMU sensor. We introduce a set of parametrized patch models and an algorithm to fit them in the environment. Potential contacts are identified as bounded curved patches of approximately the same size as the robot's foot sole. This includes sparse seed point sampling, point cloud neighborhood search, and patch fitting and validation. We also present a mapping and tracking system, where patches are maintained in a local spatial map around the robot as it moves. A bio-inspired sampling algorithm is introduced for finding salient contacts. We include a dense volumetric fusion layer for spatiotemporally tracking, using multiple depth data to reconstruct a local point cloud. We present experimental results on a mini-biped robot that performs foot placements on rocks, implementing a 3D foothold perception system, that uses the developed patch mapping and tracking framework.

cs.RO↗

arXiv2019

Cache Me If You Can: Capacitated Selfish Replication Games in Networks

In Peer-to-Peer (P2P) network systems, content (object) delivery between nodes is often required. One way to study such a distributed system is by defining games, which involve selfish nodes that make strategic choices on replicating content in their local limited memory (cache) or accessing content from other nodes for a cost. These Selfish Replication games have been introduced in [8] for nodes that do not have any capacity limits, leaving the capacitated problem, i.e. Capacitated Selfish Replication (CSR) games, open. In this work, we first form the model of the CSR games, for which we perform a Nash equilibria analysis. In particular, we focus on hierarchical networks, given their extensive use to model communication costs of content delivery in P2P systems. We present an exact polynomial-time algorithm for any hierarchical network, under two constraints on the utility functions: 1) "Nearer is better", i.e. the closest the content is to the node the less its access cost is, and 2) "Independence of irrelevant alternatives", i.e. aggregation of individual node preferences. This generalization represents a vast class of utilities and more interestingly allows each of the nodes to have simultaneously completely different functional forms of utility functions. In this general framework, we present CSR games results on arbitrary networks and outline the boundary between intractability and effective computability in terms of the network structure, object preferences, and the total number of objects. Moreover, we prove that the problem of equilibria existence becomes NP-hard for general CSR games.

cs.GT↗

arXiv2018

Center-of-Mass-Based Grasp Pose Adaptation Using 3D Range and Force/Torque Sensing

Lifting objects, whose mass may produce high wrist torques that exceed the hardware strength limits, could lead to unstable grasps or serious robot damage. This work introduces a new Center-of-Mass (CoM)-based grasp pose adaptation method, for picking up objects using a combination of exteroceptive 3D perception and proprioceptive force/torque sensor feedback. The method works in two iterative stages to provide reliable and wrist torque efficient grasps. Initially, a geometric object CoM is estimated from the input range data. In the first stage, a set of hand-size handle grasps are localized on the object and the closest to its CoM is selected for grasping. In the second stage, the object is lifted using a single arm, while the force and torque readings from the sensor on the wrist are monitored. Based on these readings, a displacement to the new CoM estimation is calculated. The object is released and the process is repeated until the wrist torque effort is minimized. The advantage of our method is the blending of both exteroceptive (3D range) and proprioceptive (force/torque) sensing for finding the grasp location that minimizes the wrist effort, potentially improving the reliability of the grasping and the subsequent manipulation task. We experimentally validate the proposed method by executing a number of tests on a set of objects that include handles, using the humanoid robot WALK-MAN.

cs.RO↗

arXiv2017

Translating Videos to Commands for Robotic Manipulation with Deep Recurrent Neural Networks

We present a new method to translate videos to commands for robotic manipulation using Deep Recurrent Neural Networks (RNN). Our framework first extracts deep features from the input video frames with a deep Convolutional Neural Networks (CNN). Two RNN layers with an encoder-decoder architecture are then used to encode the visual features and sequentially generate the output words as the command. We demonstrate that the translation accuracy can be improved by allowing a smooth transaction between two RNN layers and using the state-of-the-art feature extractor. The experimental results on our new challenging dataset show that our approach outperforms recent methods by a fair margin. Furthermore, we combine the proposed translation module with the vision and planning system to let a robot perform various manipulation tasks. Finally, we demonstrate the effectiveness of our framework on a full-size humanoid robot WALK-MAN.

cs.RO↗

arXiv2016

Curved Surface Patches for Rough Terrain Perception

Attaining animal-like legged locomotion on rough outdoor terrain with sparse foothold affordances -a primary use-case for legs vs other forms of locomotion- is a largely open problem. New advancements in control and perception have enabled bipeds to walk on flat and uneven indoor environments. But tasks that require reliable contact with unstructured world surfaces, for example walking on natural rocky terrain, need new perception and control algorithms. This thesis introduces 3D perception algorithms for contact tasks such as foot placement in rough terrain environments. We introduce a new method to identify and model potential contact areas between the robot's foot and a surface using a set of bounded curved patches. We present a patch parameterization model and an algorithm to fit and perceptually validate patches to 3D point samples. Having defined the environment representation using the patch model, we introduce a way to assemble patches into a spatial map. This map represents a sparse set of local areas potentially appropriate for contact between the robot and the surface. The process of creating such a map includes sparse seed point sampling, neighborhood searching, as well as patch fitting and validation. Various ways of sampling are introduced including a real time bio-inspired system for finding patches statistically similar to those that humans select while traversing rocky trails. These sparse patch algorithms are integrated with a dense volumetric fusion of range data from a moving depth camera, maintaining a dynamic patch map of relevant contact surfaces around a robot in real time. We integrate and test the algorithms as part of a real-time foothold perception system on a mini-biped robot, performing foot placements on rocks.

cs.RO↗