IROS 2017 Papers

Dexterous manipulation has broad applications in assembly lines, warehouses and agriculture. To perform large-scale manipulation tasks for various objects, a multi-fingered robotic hand sometimes has to sequentially adjust its grasping gestures, i.e. the finger gaits, to address the workspace limits and guarantee the object stability. However, realizing finger gaits planning in dexterous manipulation is challenging due to the complicated grasp quality metrics, uncertainties on object shapes and dynamics (mass and moment of inertia), and unexpected slippage under uncertain contact dynamics. In this paper, a dual-stage optimization based planner is proposed to handle these challenges. In the first stage, a velocity-level finger gaits planner is introduced by combining object grasp quality with hand manipulability. The proposed finger gaits planner is computationally efficient and realizes finger gaiting without 3D model of the object. In the second stage, a robust manipulation controller using robust control and force optimization is proposed to address object dynamics uncertainties and external disturbances. The dual-stage planner is able to guarantee stability under unexpected slippage caused by uncertain contact dynamics. Moreover, it does not require velocity measurement or expensive 3D/6D tactile sensors. The proposed dual-stage optimization based planner is verified by simulations on Mujoco. The simulation video is available at [1].

Fast and accurate obstacle detection is a crucial component for autonomous robot navigation. It becomes even more important for a shared control vehicle like an electric wheeled walker, since the safety of the vehicle and the user depend on the correct classification of obstacles. This work describes a method for pose estimation of four-wheeled vehicles, which utilizes the fixed resolution of digital elevation maps to generate a detailed vehicle model. The vehicle's wheels are also approximated using digital elevation maps, allowing efficient calculation of wheel to ground contact points and therefore fast and accurate estimation of valid vehicle poses. To evaluate the proposed method, pose estimates are compared to three datasets including ground truth poses: one created using an external tracking system and two created by simulations of wheeled robots. It is also shown that the method is fast enough for real time operation.

Elderly people have particular needs in performing bathing activities, since these tasks require body flexibility. Our aim is to build an assistive robotic bath system, in order to increase the independence and safety of this procedure. Towards this end, the expertise of professional carers for bathing sequences and appropriate motions has to be adopted, in order to achieve natural, physical human - robot interaction. In this paper, a real-time end-effector motion planning method for an assistive bath robot, using on-line Point-Cloud information, is proposed. The visual feedback obtained from Kinect depth sensor is employed to adapt suitable washing paths to the user's body part motion and deformable surface. We make use of a navigation function-based controller, with guarantied globally uniformly asymptotic stability, and bijective transformations for the adaptation of the paths. Experiments were conducted with a rigid rectangular object for validation purposes, while a female subject took part to the experiment in order to evaluate and demonstrate the basic concepts of the proposed methodology.

The ability to drive autonomously in heterogeneous environments without GPS, pattern identification (e.g. road following), or artificial landmarks is key to field robotics. To address this challenge, we present a complete waypoint navigation framework for unmanned ground vehicles. A Velodyne PUCK VLP-16 LiDAR and an IMU are mounted on an autonomous, full size utility vehicle and used for localization within a previously created base map. We redesign a six degrees of freedom LiDAR SLAM algorithm to achieve 3D localization on the base map, as well as real-time vehicle navigation. We fuse the low-frequency, high precision SLAM updates with high-frequency, odometric local state estimates from the vehicle. The navigation costmap consists of a 2D occupancy grid which is computed from the 3D base map. Relying on this setup, the vehicle is capable of navigating through a complex site completely autonomously. The test site has densely and sparsely built areas, bushland, industrial activities, pedestrians, and other manned or unmanned vehicles. Extensive testing was done using both current and outdated base maps for comparisons, and a high precision RTK-GPS was used for ground truth. So far, more than 60 km of completely autonomous driving has been performed without a single system or navigation failure.

Autonomous trajectory generation for unmanned aerial vehicles (UAVs) in unknown environments continues to be an important research area as UAVs become more prolific. In this paper, we develop a trajectory generation algorithm for a vehicle in an unknown environment with wind disturbances, that relies only on the vehicle's on-board distance sensors and communication with other vehicles within a finite region to generate a smooth, collision-free trajectory. The proposed trajectory generation algorithm can be used in conjunction with high-level planners and low-level motion controllers, as demonstrated. The algorithm provides guarantees that the trajectory does not violate the vehicle's thrust limitation, sensor constraints, or a user-defined clearance radius around other vehicles and obstacles. Simulation results of two quadrotors moving through an unknown building environment with obstacles demonstrates the trajectory generation performance.

There are many applications where robots have to operate in environments that other agents can change. In such cases, it is desirable for the robot to achieve a given high-level task despite interference. Ideally, the robot must decide its next action as it observes the changes in the world, i.e. act reactively. In this paper, we consider a reactive planning problem for finite robotic tasks with resource constraints. The task is represented using a temporal logic for finite behaviors and the robot must achieve the task using limited resources under all possible finite sequences of moves of other agents. We present a formulation for this problem and an approach based on quantitative games. The efficacy of the approach is demonstrated through a manipulation case study.

Exploring and mapping previously unknown environments while avoiding collisions with obstacles is a fundamental task for autonomous robots. In scenarios where this needs to be done rapidly, multi-rotors are a good choice for the task, as they can cover ground at potentially very high velocities. Flying at high velocities, however, implies the ability to rapidly plan trajectories and to react to new information quickly. In this paper, we propose an extension to classical frontier-based exploration that facilitates exploration at high speeds. The extension consists of a reactive mode in which the multi-rotor rapidly selects a goal frontier from its field of view. The goal frontier is selected in a way that minimizes the change in velocity necessary to reach it. While this approach can increase the total path length, it significantly reduces the exploration time, since the multi-rotor can fly at consistently higher speeds.

Simultaneous Localization and Mapping using RGB-D cameras has been a fertile research topic in the latest decade, due to the suitability of such sensors for indoor robotics. In this paper we propose a direct RGB-D SLAM algorithm with state-of-the-art accuracy and robustness at a los cost. Our experiments in the RGB-D TUM dataset [34] effectively show a better accuracy and robustness in CPU real time than direct RGB-D SLAM systems that make use of the GPU. The key ingredients of our approach are mainly two. Firstly, the combination of a semi-dense photometric and dense geometric error for the pose tracking (see Figure 1), which we demonstrate to be the most accurate alternative. And secondly, a model of the multi-view constraints and their errors in the mapping and tracking threads, which adds extra information over other approaches. We release the open-source implementation of our approach1. The reader is referred to a video with our results 2 for a more illustrative visualization of its performance.

This paper presents a vision-based localization system for global pose estimation of a sewer inspection robot given prior information of the sewer network from local institutions. The system is based on a Monte-Carlo Localization system that uses RGBD odometry for the prediction stage. The update step takes into account the sewer network topology for discarding wrong hypotheses. Moreover, this step is further refined whenever a discrete element of the network (i.e. manhole) is detected. To this end, another RGBD camera pointing upwards is used for precise manhole detection. A Convolutional Neural Network has been successfully trained for classifying images with and without manholes with 96% accuracy over the tested dataset. The complete system has been validated with real data obtained from the sewers of Barcelona yielding accurate localization results. All the logs and code used in the context of this paper are publicly available.

This paper presents an algorithm for surfel color and position enhancement from RGB-D data acquired across multiple image frames. Surfel-based reconstruction algorithms associate each RGB-D frame pixel to a surfel in the model. As the reconstruction progresses, surfel color and position are the average of all observations. Our proposed algorithm is designed to enhance position discontinuities and to produce sharper colors, to facilitate subsequent segmentation steps on the 3D model. During reconstruction, several colors and positions are tracked for each surfel. Only at the end of reconstruction phase the most frequent value is chosen through a Winner Takes All policy. The result has been compared to the standard averaging policy of reconstruction algorithms. Experiments have been performed using both Flood Fill and Supervoxel-LCCP segmentation and by applying two segmentation evaluation metrics. Results show that the proposed method is suitable to enhance a surfel-based model for object segmentation purposes.

Aerial surveillance and monitoring demand both real-time and robust motion detection from a moving camera. Most existing techniques for drones involve sending a video data streams back to a ground station with a high-end desktop computer or server. These methods share one major drawback: data transmission is subjected to considerable delay and possible corruption. Onboard computation can not only overcome the data corruption problem but also increase the range of motion. Unfortunately, due to limited weight-bearing capacity, equipping drones with computing hardware of high processing capability is not feasible. Therefore, developing a motion detection system with real-time performance and high accuracy for drones with limited computing power is highly desirable. In this paper, we propose a visual-inertial drone system for real-time motion detection, namely REDBEE, that helps overcome challenges in shooting scenes with strong parallax and dynamic background. REDBEE, which can run on the state-of-the-art commercial low-power application processor (e.g. Snapdragon Flight board used for our prototype drone), achieves real-time performance with high detection accuracy. The REDBEE system overcomes obstacles in shooting scenes with strong parallax through an inertial-aided dual-plane homography estimation; it solves the issues in shooting scenes with dynamic background by distinguishing the moving targets through a probabilistic model based on spatial, temporal, and entropy consistency. The experiments are presented which demonstrate that our system obtains greater accuracy when detecting moving targets in outdoor environments than the state-of-the-art real-time onboard detection systems.

Mobile robots, be it autonomous or teleoperated, require stable communication with the base station to exchange valuable information. Given the stochastic elements in radio signal propagation, such as shadowing and fading, and the possibilities of unpredictable events or hardware failures, communication loss often presents a significant mission risk, both in terms of probability and impact, especially in Urban Search and Rescue (USAR) operations. Depending on the circumstances, disconnected robots are either abandoned, or attempt to autonomously back-trace their way to the base station. Although recent results in Communication-Aware Motion Planning can be used to effectively manage connectivity with robots, there are no results focusing on autonomously re-establishing the wireless connectivity of a mobile robot without back-tracing or using detailed a priori information of the network. In this paper, we present a robust and online radio signal mapping method using Gaussian Random Fields, and propose a Resilient Communication-Aware Motion Planner (RCAMP) that integrates the above signal mapping framework with a motion planner. RCAMP considers both the environment and the physical constraints of the robot, based on the available sensory information. We also propose a self-repair strategy using RCMAP, that takes both connectivity and the goal position into account when driving to a connection-safe position in the event of a communication loss. We demonstrate the proposed planner in a set of realistic simulations of an exploration task in single or multi-channel communication scenarios.

This paper introduces RAMone, a series-elastic planar biped with knees, built to study the energetics of bipedal locomotion. RAMone is designed to achieve versatile, economical motion using lightweight legs with highly compliant joints. To demonstrate the hardware, we present a virtual-model controller that regulates body height and forward speed while walking. This controller achieves stable walking for a range of body heights, both in hardware and simulation. For these gaits, we verify that the energetic cost of transport decreases as walking height increases, in agreement with previous results for robot models and humans.

Spinal cord stimulation has enabled humans with motor complete spinal cord injury (SCI) to independently stand and recover some lost autonomic function. Quantifying the quality of bipedal standing under spinal stimulation is important for spinal rehabilitation therapies and for new strategies that seek to combine spinal stimulation and rehabilitative robots (such as exoskeletons) in real time feedback. To study the potential for automated electromyography (EMG) analysis in SCI, we evaluated the standing quality of paralyzed patients undergoing electrical spinal cord stimulation using both video and multi-channel surface EMG recordings during spinal stimulation therapy sessions. The quality of standing under different stimulation settings was quantified manually by experienced clinicians. By correlating features of the recorded EMG activity with the expert evaluations, we show that multi-channel EMG recording can provide accurate, fast, and robust estimation for the quality of bipedal standing in spinally stimulated SCI patients. Moreover, our analysis shows that the total number of EMG channels needed to effectively predict standing quality can be reduced while maintaining high estimation accuracy, which provides more flexibility for rehabilitation robotic systems to incorporate EMG recordings.

In this paper, a quadrotor optimal coverage planning approach in damaged area is considered. The quadrotor is assumed to visit a set of reachable points following the shortest path while avoiding the no-fly zones. The problem is solved by using a two-scale proposed algorithm. In the first scale, an efficient tool for cluttered environments based on optimal Rapidly-exploring Random Trees (RRT) approach, called multi-RRT* Fixed Node (RRT*FN), is developed to define the shortest paths from each point to their neighbors. Using the pair-wise costs between points provided by the first-scale algorithm, in the second scale, the overall shortest path is obtained by solving the Traveling Salesman Problem (TSP) using Genetic Algorithms (GA). Taking into consideration the limited onboard energy, a second alternative based on the well-known Vehicle Routing Problem (VRP) is used. This latter is solved using the savings heuristic approach. The effectiveness of this proposed two-scale algorithm is demonstrated through numerical simulations and promising results are obtained.

The RoboBee is a novel insect-scale flapping wing Micro Aerial Vehicle that is envisioned to enable exciting applications. While recent results have demonstrated full control as well as biomimetic behaviors such as perching, more complex challenges such as perception and navigation still exist. Typically, challenges in perception-based control can only be solved by experimentation. However, such fly-size MAVs are not widely available to researchers at large due to its intricate manufacturing process and limited mechanical lifetime. To facilitate the development of perception and control algorithms of insect-scale MAVs, we explore an approach of simulating flapping wing aerial vehicle dynamics on a quad-rotor. This work performs detailed analysis of the transformation of control inputs, and demonstrates feasibility by numerically simulating basic flight patterns of models of a RoboBee as well as that of a scaled quad-rotor.

Mobile robots operating in a shared environment with pedestrians are required to move provably safe to avoid harming pedestrians. Current approaches like safety fields use conservative obstacle models for guaranteeing safety, which leads to degraded performance in populated environments. In this paper, we introduce an online verification approach that uses information about the current pedestrian velocities to compute possible occupancies based on a kinematic model of pedestrian motion. We demonstrate that our method reduces the need for stopping while retaining safety guarantees, and thus goals are reached between 1.4 and 3.5 times faster than the standard ROS navigation stack in the tested scenarios.

Many robotic systems achieve position sensing through the use of optical encoders that specify the position of a joint to a certain resolution. Encoders effectively quantize joint space coordinates and introduce position measurement error in the process. This error propagates to operational space coordinates, limiting end-effector position and orientation resolution, and also to joint and operational space coordinate derivatives, manifesting as noise that can vitiate the signal. In this paper, we characterize encoder error in a robotic system. Given encoder specifications, robot kinematics, and discrete transfer functions mapping coordinates to their derivatives, we describe the propagation of quantization error on joint space coordinates to operational space coordinates, joint space coordinate derivatives, and operational space coordinate derivatives. We establish two results for quantization error. The first is a general result useful for establishing worst-case bounds. The second models each quantization as independent additive pseudo quantization noise (PQN) for which stochastic metrics on the error are determined. Experimental data gathered from a Phantom Premium robot/haptic device supports the analytical results.

This paper tackles the problem of generalizing robot control programs over multiple objects, tasks and environments, based on the concept of action descriptions. These are abstract, general, semantic descriptions of an action that are augmented during execution with subsymbolic parameters specific to the context at hand. The parameters are inferred through reasoning rules, which extract the context from the action description and the belief state of the robot. The proposed system scales well with increasing number of reasoning rules required to support the knowledge-intensive manipulation tasks. The architecture combines the high-level robot control program with the reasoning engine in a modular way, thus improving the scalability of the system. The approach is validated in the context of setting a table with a PR2 robot.