检索结果-内蒙古大学图书馆

GISR: Geometric Initialization and Silhouette-based Refinement for Single-View Robot Pose and Configuration Estimation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Bilić, Ivan Marić, Filip Bonsignorio, Fabio Petrović, Ivan University of Zagreb Faculty of Electrical Engineering and Computing Laboratory for Autonomous Systems and Mobile Robotics Croatia University of Toronto Institute for Aerospace Studies Space and Terrestrial Autonomous Robotic Systems Laboratory Canada

In autonomous robotics, measurement of the robot’s internal state and perception of its environment, including interaction with other agents such as collaborative robots, are essential. Estimating the pose of the robot arm from a single view has the potential to replace classical eye-to-hand calibration approaches and is particularly attractive for online estimation and dynamic environments. In addition to its pose, recovering the robot configuration provides a complete spatial understanding of the observed robot that can be used to anticipate the actions of other agents in advanced robotics use cases. Furthermore, this additional redundancy enables the planning and execution of recovery protocols in case of sensor failures or external disturbances. We introduce GISR - a deep configuration and robot-to-camera pose estimation method that prioritizes execution in real-time. GISR consists of two modules: (i) a geometric initialization module that efficiently computes an approximate robot pose and configuration, and (ii) a deep iterative silhouette-based refinement module that arrives at a final solution in just a few iterations. We evaluate GISR on publicly available data and show that it outperforms existing methods of the same class in terms of both speed and accuracy, and can compete with approaches that rely on ground-truth proprioception and recover only the pose. Our code is available at https://***/iwhitey/GISR-robot. © 2024, CC BY.

关键词：

Towards Camera Parameters Invariant Monocular Depth Estimation in autonomous Driving

学校读者我要写书评

暂无评论

Towards Camera Parameters Invariant Monocular Depth Estimati...

European Conference on mobile Robots (ECMR)

作者： Karlo Koledić Ivan Marković Ivan Petrović Faculty of Electrical Engineering and Computing Laboratory for Autonomous Systems and Mobile Robotics University of Zagreb Zagreb Croatia

Monocular depth estimation is an effective approach to environment perception due to simplicity of the sensor setup and absence of multisensor calibration. Deep learning has enabled accurate depth estimation from a single image by exploiting semantic cues such as the sizes of known objects and positions on the ground plane thereof. However, learning-based methods frequently fail to generalize on images collected with different vehicle-camera setups due to the induced perspective geometry bias. In this work, we propose an approach for camera parameters invariant depth estimation in autonomous driving scenarios. We propose a novel joint parametrization of camera intrinsic and extrinsic parameters specifically designed for autonomous driving. In order to supplement the neural network with information about the camera parameters, we fuse the proposed parametrization and image features via the novel module based on a self-attention mechanism. After thorough experimentation on the effects of camera parameter variation, we show that our approach effectively provides the neural network with useful information, thus increasing accuracy and generalization performance.

关键词：

A Distance-Geometric Method for Recovering Robot Joint Angles From an RGB Image

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Bilić, Ivan Marić, Filip Marković, Ivan Petrović, Ivan University of Zagreb Faculty of Electrical Engineering and Computing Laboratory for Autonomous Systems and Mobile Robotics Croatia University of Toronto Space and Terrestrial Autonomous Robotic Systems Laboratory Canada

autonomous manipulation systems operating in domains where human intervention is difficult or impossible (e.g., underwater, extraterrestrial or hazardous environments) require a high degree of robustness to sensing and communication failures. Crucially, motion planning and control algorithms require a stream of accurate joint angle data provided by joint encoders, the failure of which may result in an unrecoverable loss of functionality. In this paper, we present a novel method for retrieving the joint angles of a robot manipulator using only a single RGB image of its current configuration, opening up an avenue for recovering system functionality when conventional proprioceptive sensing is unavailable. Our approach, based on a distance-geometric representation of the configuration space, exploits the knowledge of a robot’s kinematic model with the goal of training a shallow neural network that performs a 2D-to-3D regression of distances associated with detected structural keypoints. It is shown that the resulting Euclidean distance matrix uniquely corresponds to the observed configuration, where joint angles can be recovered via multidimensional scaling and a simple inverse kinematics procedure. We evaluate the performance of our approach on real RGB images of a Franka Emika Panda manipulator, showing that the proposed method is efficient and exhibits solid generalization ability. Furthermore, we show that our method can be easily combined with a dense refinement technique to obtain superior results. © 2023, CC BY-NC-ND.

关键词： Manipulators

GenDepth: Generalizing Monocular Depth Estimation for Arbitrary Camera Parameters via Ground Plane Embedding

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Koledić, Karlo Petrović, Luka Petrović, Ivan Marković, Ivan University of Zagreb Faculty of Electrical Engineering and Computing Laboratory for Autonomous Systems and Mobile Robotics Zagreb Croatia

Learning-based monocular depth estimation leverages geometric priors present in the training data to enable metric depth perception from a single image, a traditionally ill-posed problem. However, these priors are often specific to a particular domain, leading to limited generalization performance on unseen data. Apart from the well studied environmental domain gap, monocular depth estimation is also sensitive to the domain gap induced by varying camera parameters, an aspect that is often overlooked in current state-of-the-art approaches. This issue is particularly evident in autonomous driving scenarios, where datasets are typically collected with a single vehicle-camera setup, leading to a bias in the training data due to a fixed perspective geometry. In this paper, we challenge this trend and introduce GenDepth, a novel model capable of performing metric depth estimation for arbitrary vehicle-camera setups. To address the lack of data with sufficiently diverse camera parameters, we first create a bespoke synthetic dataset collected with different vehicle-camera systems. Then, we design GenDepth to simultaneously optimize two objectives: (i) equivariance to the camera parameter variations on synthetic data, (ii) transferring the learned equivariance to real-world environmental features using a single real-world dataset with a fixed vehicle-camera system. To achieve this, we propose a novel embedding of camera parameters as the ground plane depth and present a novel architecture that integrates these embeddings with adversarial domain alignment. We validate GenDepth on several autonomous driving datasets, demonstrating its state-of-the-art generalization capability for different vehicle-camera systems. Copyright © 2023, The Authors. All rights reserved.

关键词： Embeddings

MOFT: Monocular odometry based on deep depth and careful feature selection and tracking

学校读者我要写书评

暂无评论

MOFT: Monocular odometry based on deep depth and careful fea...

IEEE International Conference on robotics and Automation (ICRA)

作者： Karlo Koledić Igor Cvišić Ivan Marković Ivan Petrović University of Zagreb Faculty of Electrical Engineering and Computing Laboratory for Autonomous Systems and Mobile Robotics Zagreb Croatia

autonomous localization in unknown environments is a fundamental problem in many emerging fields and the monocular visual approach offers many advantages, due to being a rich source of information and avoiding comparatively more complicated setups and multisensor calibration. Deep learning opened new venues for monocular odometry yielding not only end-to-end approaches but also hybrid methods combining the well studied geometry with specific deep components. In this paper we propose a monocular odometry that leverages deep depth within a feature based geometrical framework yielding a lightweight frame-to-frame approach with metrically scaled trajectories and state-of-the-art accuracy. The front-end is based on a multihypothesis matcher with perspective correction coupled with deep depth predictions that enables careful feature selection and tracking; especially of ground plane features that are suitable for translation estimation. The back-end is based on point-to-epipolar line minimization for rotation and unit translation estimation, followed by deep depth aided reprojection error minimization for metrically correct translation estimation. Furthermore, we also present a domain shift adaptation approach that allows for generalization over different camera intrinsic and extrinsic setups. The proposed approach is evaluated on the KITTI and KITTI-360 datasets, showing competitive results and in most cases outperforming other state-of-the-art stereo and monocular methods.

关键词：

Euclidean Equivariant Models for Generative Graphical Inverse Kinematics

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Limoyo, Oliver Marić, Filip Giamou, Matthew Alexson, Petra Petrović, Ivan Kelly, Jonathan Institute for Aerospace Studies University of Toronto Canada Laboratory for Autonomous Systems and Mobile Robotics University of Zagreb Croatia

Quickly and reliably finding accurate inverse kinematics (IK) solutions remains a challenging problem for robotic manipulation. Existing numerical solvers typically produce a single solution only and rely on local search techniques to minimize a highly nonconvex objective function. Recently, learning-based approaches that approximate the entire feasible set of solutions have shown promise as a means to generate multiple fast and accurate IK results in parallel. However, existing learning-based techniques have a significant drawback: each robot of interest requires a specialized model that must be trained from scratch. To address this shortcoming, we investigate a novel distance-geometric robot representation coupled with a graph structure that allows us to leverage the flexibility of graph neural networks (GNNs). We use this approach to train a generative graphical inverse kinematics solver (GGIK) that is able to produce a large number of diverse solutions in parallel while also generalizing well—a single learned model can be used to produce IK solutions for a variety of different robots. The graphical formulation elegantly exposes the symmetry and Euclidean equivariance of the IK problem that stems from the spatial nature of robot manipulators. We exploit this symmetry by encoding it into the architecture of our learned model, yielding a flexible solver that is able to produce sets of IK solutions for multiple robots. Copyright © 2023, The Authors. All rights reserved.

关键词： Inverse kinematics

Human Localization in Warehouse Environments based on a Wearable Camera Sensor Suite and Dynamic Ultra-Wide Band Nodes 20

学校读者我要写书评

暂无评论

Human Localization in Warehouse Environments based on a Wear...

20th International Conference on Advanced robotics, ICAR 2021

作者： Popovic, Goran Cviic, Igor Markovic, Ivan Petrovic, Ivan Laboratory For Autonomous Systems and Mobile Robotics University of Zagreb Faculty of Electrical Engineering and Computing Zagreb Croatia

ISBN: (纸本)9781665436847

Modern warehouses, equipped with an autonomous robots fleet, suffer from an efficiency deficit during human interventions in the shop floor area, since, during such interventions, all the robots must stop for safety reasons. This particularly affects large warehouses which could extremely benefit from a solution that would allow human-robot collaboration during such interventions. This solution should only stop the robots that are in the vicinity of the human and reroute the others, and it requires the following prerequisites: (i) reliable relative ranging of robots with respect to human workers that would ensure safety, and (ii) reliable localization of human workers in the warehouse. In this paper we propose a system for reliable human localization that is based on fusing cues from measured relative ranges with respect to moving robots and a camera system that is worn by the human worker. Since global locations of the robots in the warehouse are known, we use the relative ranges to robots in an indoor GPS-like fashion to provide global human location updates, while the wearable cameras provide visual odometry, i.e., the relative motion of the human, and another global cue by detecting ground fiducial markers used by robots. The fusion is performed within a graph-based optimization framework that also includes a visual odometry error model. We carried out an experimental analysis on three different datasets to validate the performance of the proposed approach and compared it to a state-of-the-art visual SLAM solution, namely ORB-SLAM2. The results demonstrate that our approach yields reliable human location within warehouse like environments. © 2021 IEEE.

关键词： Warehouses

Stereo Visual Localization Dataset Featuring Event Cameras

学校读者我要写书评

暂无评论

Stereo Visual Localization Dataset Featuring Event Cameras

European Conference on mobile Robots (ECMR)

作者： Antea Hadviger Vlaho-Josip Štironja Igor Cvišić Ivan Marković Sacha Vražić Ivan Petrović Laboratory for Autonomous Systems and Mobile Robotics University of Zagreb Faculty of Electrical Engineering and Computing Croatia Rimac Automobili Croatia

Visual odometry and SLAM methods are facing increasingly complex scenarios and novel solutions are needed to offer more accurate and reliable results in challenging environments. Standard cameras are challenged under low light conditions or very high-speed motion, as they suffer from motion blur and operate at a limited frame rate. These problems can be alleviated by using event cameras - asynchronous visual sensors that offer complementary advantages compared to standard cameras, as they do not suffer from motion blur and support high dynamic range. Although there are a number of existing datasets intended for visual odometry and SLAM that contain event data, most of them are collected using monocular sensors and limited either in terms of camera resolution or ground truth availability. Our work aims to complement this by further supporting the development of robust stereo visual odometry and SLAM algorithms, allowing to exploit both event data and intensity images. We provide both indoor sequences with 6-DoF motion and outdoor vehicle driving sequences that additionally contain 3D lidar data. All sequences contain data from a synchronized high-resolution stereo event and standard cameras, whereas ground truth trajectories are provided by either a motion capture system or a highly accurate GNSS/INS and AHRS that combines the fibre-optic gyro IMU with a dual antenna RTK GNSS receiver.

关键词：

RAVE: A Framework for Radar Ego-Velocity Estimation

学校读者我要写书评

暂无评论

RAVE: A Framework for Radar Ego-Velocity Estimation

International Conference on Multisensor Fusion and Integration for Intelligent systems (MFI)

作者： Vlaho-Josip Štironja Luka Petrović Juraj Peršić Ivan Marković Ivan Petrović Laboratory for Autonomous Systems and Mobile Robotics (LAMOR) University of Zagreb Faculty of Electrical Engineering and Computing Zagreb Croatia Calirad d.o.o. Zagreb Croatia

ISBN: (数字)9798350368031

ISBN: (纸本)9798350368048

State estimation is an essential component of autonomous systems, usually relying on sensor fusion that integrates data from cameras, LiDARs and IMUs. Recently, radars have shown the potential to improve the accuracy and robustness of state estimation and perception, especially in challenging environmental conditions such as adverse weather and low-light scenarios. In this paper, we present a framework for ego-velocity estimation, which we call RAVE, that relies on 3D automotive radar data and encompasses zero velocity detection, outlier rejection, and velocity estimation. In addition, we propose a simple filtering method to discard infeasible egovelocity estimates. We also conduct a systematic analysis of how different existing outlier rejection techniques and optimization loss functions impact estimation accuracy. Our evaluation on three open-source datasets demonstrates the effectiveness of the proposed filter and a significant positive impact of RAVE on the odometry accuracy. Furthermore, we release an opensource implementation of the proposed framework for radar ego-velocity estimation accompanied with a ROS interface.

关键词： Accuracy Three-dimensional displays Systematics Filtering Radar Trajectory Odometry State estimation Optimization Automotive engineering