IROS 2020 论文列表

Localization is one of the most important technologies needed to use Unmanned Aerial Vehicles (UAVs) in actual fields. Currently, most UAVs use GNSS to estimate their position. Recently, there have been attacks that target the weaknesses of UAVs that use GNSS, such as interrupting GNSS signal to crash the UAVs or sending fake GNSS signals to hijack the UAVs. To avoid this kind of situation, this paper proposes an algorithm that deals with the localization problem of the UAV in GNSS-denied environments. We propose a localization method, named as BRM (Building Ratio Map based) localization, for a UAV by matching an existing numerical map with UAV images. The building area is extracted from the UAV images. The ratio of buildings that occupy in the corresponding image frame is calculated and matched with the building information on the numerical map. The position estimation is started in the range of several km2 area, so that the position estimation can be performed without knowing the exact initial coordinate. Only freely available maps are used for training data set and matching the ground truth. Finally, we get real UAV images, IMU data, and GNSS data from UAV flight to show that the proposed method can achieve better performance than the conventional methods.

Focal-plane Sensor-processor (FPSP) is a next-generation camera technology which enables every pixel on the sensor chip to perform computation in parallel, on the focal plane where the light intensity is captured. SCAMP-5 is a general-purpose FPSP used in this work and it carries out computations in the analog domain before analog to digital conversion. By extracting features from the image on the focal plane, data which is digitised and transferred is reduced. As a consequence, SCAMP-5 offers a high frame rate while maintaining low energy consumption. Here, we present BITVO, which is the first 6-Degrees of Freedom visual odometry algorithm which utilises the FPSP. Our entire system operates at 300 FPS in a natural environment, using binary edges and corner features detected by the SCAMP-5.

Predicting and planning interactive behaviors in complex traffic situations presents a challenging task. Especially in scenarios involving multiple traffic participants that interact densely, autonomous vehicles still struggle to interpret situations and to eventually achieve their own mission goal. As driving tests are costly and challenging scenarios are hard to find and reproduce, simulation is widely used to develop, test, and benchmark behavior models. However, most simulations rely on datasets and simplistic behavior models for traffic participants and do not cover the full variety of real-world, interactive human behaviors. In this work, we introduce BARK, an open-source behavior benchmarking environment designed to mitigate the shortcomings stated above. In BARK, behavior models are (re-)used for planning, prediction, and simulation. A range of models is currently available, such as MonteCarlo Tree Search and Reinforcement Learning-based behavior models. We use a public dataset and sampling-based scenario generation to show the inter-exchangeability of behavior models in BARK. We evaluate how well the models used cope with interactions and how robust they are towards exchanging behavior models. Our evaluation shows that BARK provides a suitable framework for a systematic development of behavior models.

In this paper, we propose a mapping technique that builds a continuous representation of the environment from range data. The strategy presented here encodes the probability of points in space to be occupied using 2.5D B-spline surfaces. For a fast update rate, the surface is recursively updated as new measurements arrive. The proposed B-spline map is less susceptible to precision and interpolation errors that are present in occupancy grid-based methods. From simulation and experimental results, we show that this approach leverages the floating point resolution of continuous metric maps and the fast update/access/merging advantages of discrete metric maps. Thus, the proposed method is suitable for online robotic tasks such as localization and path planning, requiring minor modification to existing software that usually operates on metric maps.

The use of robots in minimally invasive surgery has improved the quality of standard surgical procedures. So far, only the automation of simple surgical actions has been investigated by researchers, while the execution of structured tasks requiring reasoning on the environment and the choice among multiple actions is still managed by human surgeons. In this paper, we propose a framework to implement surgical task automation. The framework consists of a task-level reasoning module based on answer set programming, a low-level motion planning module based on dynamic movement primitives, and a situation awareness module. The logic-based reasoning module generates explainable plans and is able to recover from failure conditions, which are identified and explained by the situation awareness module interfacing to a human supervisor, for enhanced safety. Dynamic Movement Primitives allow to replicate the dexterity of surgeons and to adapt to obstacles and changes in the environment. The framework is validated on different versions of the standard surgical training peg-and-ring task.

Large-scale 3D autonomous self-reconfigurable modular robots are made of numerous interconnected robotic modules that operate in a close packing. The modules are assumed to have their own CPU and memory, and are only able to communicate with their direct neighbors. As such, the robots embody a special computing architecture: a distributed memory and distributed CPU system with a local message-passing interface. The modules can move and rearrange themselves changing the robot's connection topology. This may potentially cause mechanical failures (e.g., overloading of some inter-modular connections), which are irreversible and need to be detected in advance. In the present contribution, we further develop the idea of performing model-based detection of mechanical failures, posed in the form of balance equations solved by the modular robot itself in a distributed manner. A special implementation of the Conjugate Gradient iterative solution method is proposed and shown to greatly reduce the required number of iterations compared with the weighted Jacobi method used previously. The algorithm is verified in a virtual test bed-the VisibleSim emulator of the modular robot. The assessments of time-, CPU-, communication- and memory complexities of the proposed scheme are provided.

With the recent development of autonomous vehicle technology, there have been active efforts on the deployment of this technology at different scales that include urban and highway driving. While many of the prototypes showcased have been shown to operate under specific cases, little effort has been made to better understand their shortcomings and generalizability to new areas. Distance, uptime and number of manual disengagements performed during autonomous driving provide a high-level idea on the performance of an autonomous system but without proper data normalization, testing location information, and the number of vehicles involved in testing, the disengagement reports alone do not fully encompass system performance and robustness. Thus, in this study a complete set of metrics are applied for benchmarking autonomous vehicle systems in a variety of scenarios that can be extended for comparison with human drivers and other autonomous vehicle systems. These metrics have been used to benchmark UC San Diego's autonomous vehicle platforms during early deployments for micro-transit and autonomous mail delivery applications.

This paper serves as one of the first efforts to enable large-scale and long-duration autonomy using the Boston Dynamics Spot robot. Motivated by exploring extreme environments, particularly those involved in the DARPA Subterranean Challenge, this paper pushes the boundaries of the state-of-practice in enabling legged robotic systems to accomplish real-world complex missions in relevant scenarios. In particular, we discuss the behaviors and capabilities which emerge from the integration of the autonomy architecture NeBula (Networked Belief-aware Perceptual Autonomy) with next-generation mobility systems. We will discuss the hardware and software challenges, and solutions in mobility, perception, autonomy, and very briefly, wireless networking, as well as lessons learned and future directions. We demonstrate the performance of the proposed solutions on physical systems in real-world scenarios.3 The proposed solution contributed to winning 1st-place in the 2020 DARPA Subterranean Challenge, Urban Circuit.4

In this paper, we propose an autonomous method for robot navigation based on a multi-camera setup that takes advantage of a wide field of view. A new multi-task network is designed for handling the visual information supplied by the left, central and right cameras to find the passable area, detect the intersection and infer the steering. Based on the outputs of the network, three navigation indicators are generated and then combined with the high-level control commands extracted by the proposed MapNet, which are finally fed into the driving controller. The indicators are also used through the controller for adjusting the driving velocity, which assists the robot to adjust the speed for smoothly bypassing obstacles. Experiments in real-world environments demonstrate that our method performs well in both local obstacle avoidance and global goal-directed navigation tasks.

This paper presents an industrial staircase localization algorithm based on RGBD data from a tracked robot. This situation is really challenging as the camera is placed close to the ground. Moreover, RGBD can be really noisy on sparse staircases. Contrary to existing works, our evaluation relies on ground truth data provided by a motion capture system. Our experiments suggest that our algorithm can robustly locate industrial staircase. We also propose a new framework to evaluate stair localization performance from RGBD data. The overall performance allows to safety control a robot to rally the staircase.

This paper proposes a planning algorithm for autonomous media production with multiple Unmanned Aerial Vehicles (UAVs) in outdoor events. Given filming tasks specified by a media Director, we formulate an optimization problem to maximize the filming time considering battery constraints. As we conjecture that the problem is NP-hard, we consider a discretization version, and propose a graph-based algorithm that can find an optimal solution of the discrete problem for a single UAV in polynomial time. Then, a greedy strategy is applied to solve the problem sequentially for multiple UAVs. We demonstrate that our algorithm is efficient for small teams (3-5 UAVs) and that its performance is close to the optimum. We showcase our system in field experiments carrying out actual media production in an outdoor scenario with multiple UAVs.

UAVs face many challenges in autonomous obstacle avoidance in large outdoor scenarios, specifically the long communication distance from ground stations. The computing power of onboard computers is limited, and the unknown obstacles cannot be accurately detected. In this paper, an autonomous obstacle avoidance scheme based on the fusion of millimeter wave radar and monocular camera is proposed. The visual detection is designed to detect unknown obstacles which is more robust than traditional algorithms. Then extended Kalman filter (EKF) data fusion is used to build exact real 3D coordinates of the obstacles. Finally, an efficient path planning algorithm is used to obtain the path to avoid obstacles. Based on the theoretical design, an experimental platform is built to verify the UAV autonomous obstacle avoidance scheme proposed in this paper. The experiment results show the proposed scheme cannot only detect different kinds of unknown obstacles, but can also take up very little computing resources to run on an onboard computer. The outdoor flight experiment shows the feasibility of the proposed scheme.

The ocean world Europa is a prime target for exploration given its potential habitability [1]. We propose a mobile robotic system that is capable of autonomously traversing tens of meters to visit multiple sites of interest on a Europan analogue surface. Due to the topology of Europan terrain being largely unknown, it is desired that this mobility system traverse a large variety of terrain types. The mobility system should also be capable of crossing unstructured terrain in an autonomous manner given the communications limitations between Earth and Europa.A wheel-on-limb robotic rover is presented that may actively conform to terrain features up to 1.5 wheel diameters tall while driving. The robot uses a sampling-based motion planner to generate paths that leverage its unique locomotive capabilities. The planner assesses terrain hazards and wheel workspace limits as obstacles. It may also select a mobility mode based on predicted energy usage and the need for limb articulation on the terrain being traversed. This autonomous mobility was evaluated on chaotic salt-evaporite terrain found in Death Valley, CA, an analogue to the Europan surface. Over the course of 38 trials, the rover autonomously traversed 435m of extreme terrain while maintaining a rate of 0.64 traverse ending failures for every 10m driven.

Autonomous navigation in complex environments is a crucial task in time-sensitive scenarios such as disaster response or search and rescue. However, complex environments pose significant challenges for autonomous platforms to navigate due to their challenging properties: constrained narrow passages, unstable pathway with debris and obstacles, or irregular geological structures and poor lighting conditions. In this work, we propose a multimodal fusion approach to address the problem of autonomous navigation in complex environments such as collapsed cites, or natural caves. We first simulate the complex environments in a physics-based simulation engine and collect a large-scale dataset for training. We then propose a Navigation Multimodal Fusion Network (NMFNet) which has three branches to effectively handle three visual modalities: laser, RGB images, and point cloud data. The extensively experimental results show that our NMFNet outperforms recent state of the art by a fair margin while achieving real-time performance. We further show that the use of multiple modalities is essential for autonomous navigation in complex environments. Finally, we successfully deploy our network to both simulated and real mobile robots.

This paper presents combined velocity-heading control of a planar snake robot for the autonomous navigation and obstacle avoidance in a simulation environment. The kinematics and dynamics of the snake robot were derived using the articulated-body algorithm without considering the non-holonomic constraints. A double-layer controller was designed to control both heading direction and average velocity through joint motion control. We adopted a rule-based expert system for autonomous navigation while avoiding obstacles/restricted-areas. The guidance commands were realized by two proportional controllers that use feedback of the estimated speed and heading of the robot. To validate the combined velocity-heading controller, a series of simulations were carried out for a snake robot with 6 links (8 DOF). The autonomous navigation and obstacle-avoidance algorithms provided the commands to follow the desired trajectories. The simulation results showed the effectiveness of the controller in following the desired heading directions and achieving targeted velocities with small errors to reach the goal position by avoiding obstacles.

To allow for the construction of large space structures to support future space endeavors, autonomous robotic solutions would serve to reduce cost and risk of human extravehicular activity (EVA). Practicality of autonomous assembly requires both theoretical and algorithmic advances, and hardware experimentation across a spectrum of technological readiness levels. Analysis of hardware experiments provides novel insights not readily apparent in simulations alone, which serves to inform future developments.This paper describes analysis and insights gained from an autonomous assembly experiment consisting of a dexterous manipulator, a gross positioning serial arm, and a 1 degree of freedom (DOF) turntable to facilitate the assembly and deployment of a solar array mockup. This experiment combined state estimation in an uncertain environment with contact-heavy operations such as grasping, self-reconfiguring, joining, and deploying. Insights gained are presented due to their applicability to other field-based manipulation tasks by a team of robots.

We consider an autonomous exploration problem in which a range-sensing mobile robot is tasked with accurately mapping the landmarks in an a priori unknown environment efficiently in real-time; it must choose sensing actions that both curb localization uncertainty and achieve information gain. For this problem, belief space planning methods that forward- simulate robot sensing and estimation may often fail in real-time implementation, scaling poorly with increasing size of the state, belief and action spaces. We propose a novel approach that uses graph neural networks (GNNs) in conjunction with deep reinforcement learning (DRL), enabling decision-making over graphs containing exploration information to predict a robot's optimal sensing action in belief space. The policy, which is trained in different random environments without human intervention, offers a real-time, scalable decision-making process whose high-performance exploratory sensing actions yield accurate maps and high rates of information gain.

Current approaches to physical security suffer from high false alarm rates and frequent human operator involvement, despite the relative rarity of real-world threats. We present a novel architecture for autonomous adaptive physical security called autonomous detection and assessment with moving sensors (ADAMS). ADAMS is a framework for reducing nuisance and false alarms by placing mobile robotic platforms equipped with sensors outside the normal asset perimeter. These robotic agents integrate sensor data from multiple perspectives over time, and autonomously move to obtain the best new data to reduce uncertainty in the threat scene. Inferences drawn from data fused over time provide ultimate decisions regarding whether to alert human operators. This paper describes the framework and algorithms used in a prototype ADAMS implementation. We describe the results of simulations comparing this framework to alternate paradigms. These simulations show ADAMS has a 4x increase in the range at which threats are identified versus traditional static sensors, and a 5x reduction in false alarms triggered versus frameworks where all sensor detections become alarms, leading to reduced operator load. Further, these simulations show this framework for reacting to new potential threats significantly outperforms methods which merely patrol the site. We also present the results of preliminary hardware trials of an exemplar prototype system, providing limited validation of the simulations in a real-time physical demonstration.

Many self-driving vehicles use a multi-sensor system comprising multiple 3D LiDAR and radar sensors for robust all-round perception. Precise calibration of this multi-sensor system is a critical prerequisite for accurate perception data which facilitates safe operation of self-driving vehicles in highly dynamic urban environments. This paper proposes the first-known automatic targetless method for extrinsic calibration of multiple 3D LiDAR and radar sensors, and which only requires the vehicle to be driven over a short distance. The proposed method first estimates the 6-DoF pose of each LiDAR sensor with respect to the vehicle reference frame by minimizing point-to-plane distances between scans from different LiDAR sensors. In turn, a 3D map of the environment is built using data from all calibrated LiDAR sensors on the vehicle. We find the 6-DoF pose of each radar sensor with respect to the vehicle reference frame by minimizing (1) point-to-plane distances between radar scans and the 3D map, and (2) radial velocity errors. Our proposed calibration method does not require overlapping fields of view between LiDAR and radar sensors. Real-world experiments demonstrate the accuracy and repeatability of the proposed calibration method.