Real Robot Data Research Articles

Introspective perception for mobile robots

Perception algorithms that provide estimates of their uncertainty are crucial to the development of autonomous robots that can operate in challenging and uncontrolled environments. Such perception algorithms provide the means for having risk-aware robots that reason about the probability of successfully completing a task when planning. There exist perception algorithms that come with models of their uncertainty; however, these models are often developed with assumptions, such as perfect data associations, that do not hold in the real world. Hence the resultant estimated uncertainty is a weak lower bound. To tackle this problem we present introspective perception — a novel approach for predicting accurate estimates of the uncertainty of perception algorithms deployed on mobile robots. By exploiting sensing redundancy and consistency constraints naturally present in the data collected by a mobile robot, introspective perception learns an empirical model of the error distribution of perception algorithms in the deployment environment and in an autonomously supervised manner. In this paper, we present the general theory of introspective perception and demonstrate successful implementations for two different perception tasks. We provide empirical results on challenging real-robot data for introspective stereo depth estimation and introspective visual simultaneous localization and mapping and show that they learn to predict their uncertainty with high accuracy and leverage this information to significantly reduce state estimation errors for an autonomous mobile robot.

From the Dexterous Surgical Skill to the Battlefield—A Robotics Exploratory Study

Short response time is critical for future military medical operations in austere settings or remote areas. Such effective patient care at the point of injury can greatly benefit from the integration of semi-autonomous robotic systems. To achieve autonomy, robots would require massive libraries of maneuvers collected with the goal of training machine learning algorithms. Although this is attainable in controlled settings, obtaining surgical data in austere settings can be difficult. Hence, in this article, we present the Dexterous Surgical Skill (DESK) database for knowledge transfer between robots. The peg transfer task was selected as it is one of the six main tasks of laparoscopic training. In addition, we provide a machine learning framework to evaluate novel transfer learning methodologies on this database. A set of surgical gestures was collected for a peg transfer task, composed of seven atomic maneuvers referred to as surgemes. The collected Dexterous Surgical Skill dataset comprises a set of surgical robotic skills using the four robotic platforms: Taurus II, simulated Taurus II, YuMi, and the da Vinci Research Kit. Then, we explored two different learning scenarios: no-transfer and domain-transfer. In the no-transfer scenario, the training and testing data were obtained from the same domain; whereas in the domain-transfer scenario, the training data are a blend of simulated and real robot data, which are tested on a real robot. Using simulation data to train the learning algorithms enhances the performance on the real robot where limited or no real data are available. The transfer model showed an accuracy of 81% for the YuMi robot when the ratio of real-tosimulated data were 22% to 78%. For the Taurus II and the da Vinci, the model showed an accuracy of 97.5% and 93%, respectively, training only with simulation data. The results indicate that simulation can be used to augment training data to enhance the performance of learned models in real scenarios. This shows potential for the future use of surgical data from the operating room in deployable surgical robots in remote areas.

Cooperative Localization of Drones by using Interval Methods

In this article we address the problem of cooperative pose estimation in a group of unmanned aerial vehicles (UAV) in a bounded error context. The UAVs are equipped with cameras to track landmarks positions, and a communication and ranging system to cooperate with their neighbours. Measurements are represented by intervals, and constraints are expressed on the robots poses (positions and orientations). Each robot of the group first computes a pose domain using only its sensors measurements using set inversion via interval analysis. Then, through position boxes exchange, positions are cooperatively refined by constraint propagation in the group. Results with real robot data are presented, and show that the position accuracy is improvedthanks to cooperation.

Improved Visual-Inertial Localization for Low-cost Rescue Robots

This paper improves visual-inertial systems to boost the localization accuracy for low-cost rescue robots. When robots traverse on rugged terrain, the performance of pose estimation suffers from big noise on the measurements of the inertial sensors due to ground contact forces, especially for low-cost sensors. Therefore, we propose Threshold-based and Dynamic Time Warping-based methods to detect abnormal measurements and mitigate such faults. The two methods are embedded into the popular VINS-Mono system to evaluate their performance. Experiments are performed on simulation and real robot data, which show that both methods increase the pose estimation accuracy. Moreover, the Threshold-based method performs better when the noise is small and the Dynamic Time Warping-based one shows greater potential on large noise.

Simultaneously merging multi-robot grid maps at different resolutions

For an unknown GPS-denied environment, multiple robots can explore various areas of the same environment and build local maps for these areas. Accordingly, it is essential to merge these local maps of different robots into one global map. For grid map merging, this paper proposes an effective approach, which can simultaneously merge multi-robot grid maps at different resolutions. First, we present a scaling pairwise method for merging grid map pairs. Usually, a selected grid map is initialized as the seed map, which is then sequentially updated by performing scaling pairwise merging between itself and other input grid maps. Afterwards, map augmentation and feature fusion strategy is proposed to alternatively integrate two local maps into one initial global map. To address the accumulated error, a coarse-to-fine method is introduced to refine the initial global map and obtain the accurate global map. Experimental results conducted on real robot data sets demonstrate that the proposed approach can merge multiple grid maps simultaneously at different resolutions with good performances.

Simultaneous Merging Multiple Grid Maps Using the Robust Motion Averaging

Mapping in the GPS-denied environment is an important and challenging task in the field of robotics. In the large environment, mapping can be significantly accelerated by multiple robots exploring different parts of the environment. Accordingly, a key problem is how to integrate these local maps built by different robots into a single global map. In this paper, we propose an approach for simultaneous merging of multiple grid maps by the robust motion averaging. The main idea of this approach is to recover all global motions for map merging from a set of relative motions. Therefore, it firstly adopts the pair-wise map merging method to estimate relative motions for grid map pairs. To obtain as many reliable relative motions as possible, a graph-based sampling scheme is utilized to efficiently remove unreliable relative motions obtained from the pair-wise map merging. Subsequently, the accurate global motions can be recovered from the set of reliable relative motions by the motion averaging. Experimental results carried on real robot data sets demonstrate that proposed approach can achieve simultaneous merging of multiple grid maps with good performances.

Object Recognition in 3D Point Clouds Using Web Data and Domain Adaptation

In recent years, object detection has become an increasingly active field of research in robotics. An important problem in object detection is the availability of a sufficient amount of labeled training data to learn good classifiers. In this paper we show how to significantly reduce the need for manually labeled training data by leveraging data sets available on the World Wide Web. Specifically, we show how to use objects from Google’s 3D Warehouse to train an object detection system for 3D point clouds collected by robots navigating through both urban and indoor environments. In order to deal with the different characteristics of the web data and the real robot data, we additionally use a small set of labeled point clouds and perform domain adaptation. Our experiments demonstrate that additional data taken from the 3D Warehouse along with our domain adaptation greatly improves the classification accuracy on real-world environments.

A SLAM Approach by Combining ICP Algorithm and Particle Filter

摘要: 为了实现移动机器人仅依靠激光测距仪和里程计实时地创建精确的栅格地图, 本文提出了一种结合最近点迭代(Iterative closest point, ICP)算法和Rao-Blackwellized粒子滤波的同时定位与地图创建方法. 该方法利用ICP算法对相邻两次激光扫描数据进行配准, 并将配准结果代替误差较大的里程计读数, 以改善基于里程计读数的建议分布函数; 同时通过采用改进的抽样策略, 提高了粒子滤波过程中的抽样效率, 降低创建地图所需的粒子数. 仿真结果表明了该方法的有效性. 关键词: 同时定位与地图创建 / 最近点迭代法 / Rao-Blackwellized粒子滤波 / 建议分布函数

Learning Geometrically-Constrained Hidden Markov Models for Robot Navigation: Bridging the Topological-Geometrical Gap

Hidden Markov models (HMMs) and partially observable Markov decision processes (POMDPs) provide useful tools for modeling dynamical systems. They are particularly useful for representing the topology of environments such as road networks and office buildings, which are typical for robot navigation and planning. The work presented here describes a formal framework for incorporating readily available odometric information and geometrical constraints into both the models and the algorithm that learns them. By taking advantage of such information, learning HMMs/POMDPs can be made to generate better solutions and require fewer iterations, while being robust in the face of data reduction. Experimental results, obtained from both simulated and real robot data, demonstrate the effectiveness of the approach.