IROS 2016 论文列表

Monitoring and predicting water quality poses significant challenges. Collecting enough information to characterize bodies of water is a critical bottleneck. Collecting data and samples from the surface all the way to the bottom over a short period of time would give water scientists the best spatio-temporal picture. In this paper, we present a small, light-weight, inexpensive water sensing and sampling robot, the “Waterbug”, capable of descending to depths up to 10m, collecting sensor information and a water sample, and returning to the surface. The water sampler also has limited capability to adjust buoyancy to hold depth for the purpose of measuring environmental conditions at specific locations in the water column. It is small enough that a single scientist could carry several in a backpack or it could be deployed by other robotic systems. The low cost of the node makes it feasible for blanket deployment. No tools are required for field servicing and the sample collection chamber is a common syringe that can be swapped quickly for redeployment. The main challenge was developing the system model and algorithm for achieving neutral buoyancy in the presence of system and initial condition variance. Over a range of conditions, we were able to achieve an 80% success rate for meeting the neutral buoyancy criteria and a 100% success rate in capturing a sample and returning to the surface.

The remarkable ability of goats to maintain stability during climbing cliffs or trees provides a valuable opportunity to understand some of the secrets of stable legged locomotion on unstructured terrains. This paper, for the first time, presents analytical and experimental explanations as to how the morphological computation at the goat hoof makes a significant contribution to slip reduction on both smooth and rough surfaces. We conducted experiments using a laboratory made hoof and compared its dynamic behavior against a rounded foot. We recorded forces and position of the hoof to analyze the effect of its shape and the individual contributions from 3-joints in the hoof on the work required to slip. Results state that the work required to move the hoof is more than 3 times that required to move a rounded foot. Additionally, the variables in the transient state are affected not only by the number and type of joints but also by the interaction with the environment. These findings promote the development of new types of feet for robots for all terrain conditions with greater stability and less control complexity.

In this paper we propose an on-line system that discovers and drives collision-free traversable paths, using a variational approach to dense stereo vision. Our system is light weight, can be run on low cost hardware and is remarkably quick to predict the semantics. In addition to the scene's path affordance it yields a segmentation of the local scene as a composite of distinctive labels - e.g, ground, sky, obstacles and vegetation. To estimate the labels, we combine a very fast and light weight (shallow) image classifier which considers informative feature channels derived from colour images and dense depth maps estimates. Unlike other approaches, we do not use local descriptors around pixel features. Instead, we encompass label-predicted probabilities with a variational approach for image segmentation. Akin to dense depth map estimation, we obtain semantically segmented images by means of convex regularisation. We show how our system can rapidly obtain the required semantics and paths at VGA resolution. Extensive experiments on the KITTI dataset support the robustness of our system to derive collision-free local routes. An accompanied video supports the robustness of the system at live execution in an outdoor experiment.

We consider the problem of estimating the wind velocity perceived by a flying multicopter, from data acquired by onboard sensors and knowledge of its aerodynamics model only. We employ two complementary methods. The first is based on the estimation of the external wrench (force and torque) due to aerodynamics acting on the robot in flight. Wind velocity is obtained by inverting an identified model of the aerodynamic forces. The second method is based on the estimation of the propeller aerodynamic power, and provides an estimate independent of other sensors. We show how to calculate components of the wind velocity using multiple aerodynamic power measurements, when the poses between them are known. The method uses the motor current and angular velocity as measured by the electronic speed controllers, essentially using the propellers as wind sensors. Verification of the methods and model identification were done using measurements acquired during autonomous flights in a 3D wind tunnel.

In this paper, we developed a small wheel-legged mobile robot system, which could walk on different road environments using wheels or legs. It is composed of mechanical, sensor and control subsystems. The mechanical subsystem includes a wheel-legged mobile platform, a rigid robotic arm and a flexible arm. The mobile platform provides a variety of movement ways to meet the requirement of different mobility. The rigid arm (denoted by arm-a) is a serial manipulator with 4-DOFs. It can be used to grasp and manipulate payloads. The flexible arm (denoted by arm-b) is a manipulator with continuous curve, and a camera is mounted on arm-b. So it can be used to provide visual inspection and measurement information. The sensor subsystem is composed of ultrasonic sensors mounted on the platform and a WIFI camera mounted on arm-b. It provides measurement information and visual inspection for remote control. The control subsystem includes an embedded controller and a PC computer. The former is developed based on an ARM microprocessor, on which the real-time operation system-RT-Thread system runs. The mission decomposition and trajectory planning algorithms are programed in C language and run in the PC. At last, typical experiments are performed. Experiment results verified the robot's mobility, operation capability and remote-control function.

The task of coverage path planning in 2D indoor and outdoor environments is classified as a NP-hard problem, and has been an active research topic for over 30 years. We derive a novel, exact cellular decomposition method called the Constriction Decomposition Method (CDM) and apply it to complex indoor environments. The CDM rapidly identifies constriction points in the environment and decomposes the environment into easily traversable cells by exploiting the geometric information contained in the environment's straight skeleton. Several heuristic path planning methods that find paths that completely cover each cell are explored. We apply our method on a complex indoor office-like environment and compare our results to existing methods.

Finding and retrieving resources in unmapped environments is an important and difficult challenge for robot swarms. Central-place foraging algorithms can be tuned to produce efficient collective strategies for different resource distributions. However, efficiency decreases as swarm size scales up: larger swarms produce more inter-robot collisions and increase competition for resources. We propose a novel extension to central-place foraging in which multiple nests are distributed in the environment. In this multiple-place foraging algorithm, robots depart from a home nest but always return to the nest closest to them. We simulate robot swarms that mimic foraging ants using the multiple-place strategy, employing a genetic algorithm to optimize their behavior in the robot simulator ARGoS. Experiments show that multiple nests produce higher foraging rates and lower average travel time compared to central-place foraging for three different resource distributions. Time spent avoiding robot-robot collisions is not always reduced as was expected, primarily because the use of pheromone-like waypoints leads to more collisions when robots forage for clustered resources. These results demonstrate the importance of careful design in order to create efficient multiple collection points to mitigate the central-place bottleneck for foraging robot swarms.

This paper introduces the CableRobot simulator, which was developed at the Max Planck Institute for Biological Cybernetics in cooperation with the Fraunhofer Institute for Manufacturing Engineering and Automation IPA. The simulator is a completely novel approach to the design of motion simulation platforms in so far as it uses cables and winches for actuation instead of rigid links known from hexapod simulators. This approach allows to reduce the actuated mass, scale up the workspace significantly, and provides great flexibility to switch between system configurations in which the robot can be operated. The simulator will be used for studies in the field of human perception research and virtual reality applications. The paper dicusses some of the issues arising from the usage of cables and provides a system overview regarding kinematics and system dynamics as well as giving a brief introduction into possible application use cases.

Reliable detection and avoidance of obstacles is a crucial prerequisite for autonomously navigating robots as both guarantee safety and mobility. To ensure safe mobility, the obstacle detection needs to run online, thereby taking limited resources of autonomous systems into account. At the same time, robust obstacle detection is highly important. Here, a too conservative approach might restrict the mobility of the robot, while a more reckless one might harm the robot or the environment it is operating in. In this paper, we present a terrain-adaptive approach to obstacle detection that relies on 3D-Lidar data and combines computationally cheap and fast geometric features, like step height and steepness, which are updated with the frequency of the lidar sensor, with semantic terrain information, which is updated with at lower frequency. We provide experiments in which we evaluate our approach on a real robot on an autonomous run over several kilometers containing different terrain types. The experiments demonstrate that our approach is suitable for autonomous systems that have to navigate reliable on different terrain types including concrete, dirt roads and grass.

Motions of a robot interacting with its environment can be described by a set of constraints. This paper introduces an approach, called motion template, which can quickly program and compose the constraints for the motion planner to generate the trajectory. Two types of motion templates, grasp and turn, are specifically described to explain the details of the technique. The reusability and shareability properties of the motion template are demonstrated using a variety of the motion planning applications across different robot platforms. A motion template framework is used to implement the motion template with the trajectory optimization.

This paper addresses the problem of jointly planning both grasps and subsequent manipulative actions. Previously, these two problems have typically been studied in isolation, however joint reasoning is essential to enable robots to complete real manipulative tasks. In this paper, the two problems are addressed jointly and a solution that takes both into consideration is proposed. To do so, a manipulation capability index is defined, which is a function of both the task execution waypoints and the object grasping contact points. We build on recent state-of-the-art grasp-learning methods, to show how this index can be combined with a likelihood function computed by a probabilistic model of grasp selection, enabling the planning of grasps which have a high likelihood of being stable, but which also maximise the robot's capability to deliver a desired post-grasp task trajectory. We also show how this paradigm can be extended, from a single arm and hand, to enable efficient grasping and manipulation with a bi-manual robot. We demonstrate the effectiveness of the approach using experiments on a simulated as well as a real robot.

The different strategies for feature extraction and synthesis employed by humans and computers are often complementary, hence combining the two into an integrated object recognition system may considerably improve performance over either used in isolation. Rapid Serial Visual Presentation (RSVP) is one well-established technique that has shown promise integrating human perception into a machine perception system. In this paper, we apply computer vision techniques to image data filtered through human RSVP. We introduce “task conversions” to integrate the two modalities, applying the precise localization capabilities of computer vision with the detection capabilities of RSVP. We employ naive Bayesian fusion and a novel method, dynamic belief fusion (DBF), in a joint scheme as fusion approaches. Preliminary experiments demonstrate that DBF extracts complementary information from both human and machine sources to improve performance for both target classification and object detection.

The design of legged robots is often inspired by animals evolved to excel at different tasks. However, while mimicking morphological features seen in nature can be very powerful, robots may need to perform motor tasks that their living counterparts do not. In the absence of designs that can be mimicked, an alternative is to resort to mathematical models that allow the relationship between a robot's form and function to be explored. In this paper, we propose such a model to co-design the motion and leg configurations of a robot such that a measure of performance is optimized. The framework begins by planning trajectories for a simplified model consisting of the center of mass and feet. The framework then optimizes the length of each leg link while solving for associated full-body motions. Our model was successfully used to find optimized designs for legged robots performing tasks that include jumping, walking, and climbing up a step. Although our results are preliminary and our analysis makes a number of simplifying assumptions, our findings indicate that the cost function, the sum of squared joint torques over the duration of a task, varies substantially as the design parameters change.

In this paper, we propose a framework for prioritized constraint-based specification of robot tasks. This framework is integrated with a cognitive robotic system based on semantic models of processes, objects, and workcells. The target is to enable intuitive (re-)programming of robot tasks, in a way that is suitable for non-expert users typically found in SMEs. Using CAD semantics, robot tasks are specified as geometric inter-relational constraints. During execution, these are combined with constraints from the environment and the workcell, and solved in real-time. Our constraint model and solving approach supports a variety of constraint functions that can be non-linear and also include bounds in the form of inequalities, e.g., geometric inter-relations, distance, collision avoidance and posture constraints. It is a hierarchical approach where priority levels can be specified for the constraints, and the nullspace of higher priority constraints is exploited to optimize the lower priority constraints. The presented approach has been applied to several typical industrial robotic use-cases to highlight its advantages compared to other state-of-the-art approaches.

We investigate a variation of the art gallery problem in which a team of mobile guards tries to track an unpredictable intruder in a simply-connected polygonal environment. The guards are confined to move along the diagonals of a polygon, and are deployed according to the strategy proposed in [1] that provides an upper bound of ⌊ n/4 ⌋ mobile guards to cover a simply-connected polygonal environment. We introduce the concept of critical regions to generate event-triggered strategies for the guards. Based on these strategies, we present sufficient conditions for ⌊ n/4 ⌋ guards to track an unpredictable mobile intruder forever.

In this paper we face the challenging problem of takeoff and landing on sloped surfaces for a VTOL aerial vehicle. We define the general conditions for a safe and robust maneuver and we analyze and compare two classes of methods to fulfill these conditions: free-flight vs. passively-tethered. Focusing on the less studied tethered method, we show its advantages w.r.t. the free-flight method thanks to the possibility of inclined hovering equilibria. We prove that the tether configuration and the inclination of the aerial vehicle w.r.t. the slope are flat outputs of the system and we design a hierarchical nonlinear controller based on this property. We then show how this controller can be used to land and takeoff in a robust way without the need of either a planner or a perfect tracking. The validity and applicability of the method in the real world is shown by experiments with a quadrotor that is able to perform a safe landing and takeoff on a sloped surface.

Diagnostic blood testing is the most prevalent medical procedure performed in the world and forms the cornerstone of modern health care delivery. Yet blood tests are still predominantly carried out in centralized labs using large-volume samples acquired by manual venipuncture, and no end-to-end solution from blood draw to sample analysis exists today. Our group is developing a platform device that merges robotic phlebotomy with automated diagnostics to rapidly deliver patient information at the site of the blood draw. The system couples an image-guided venipuncture robot, designed to address the challenges of routine venous access, with a centrifuge-based blood analyzer to obtain quantitative measurements of hematology. In this paper, we first present the system design and architecture of the integrated device. We then perform a series of in vitro experiments to evaluate the cannulation accuracy of the system on blood vessel phantoms. Next, we assess the effects of vessel diameter, needle gauge, flow rate, and viscosity on the rate of sample collection. Finally, we demonstrate proof-of-concept of a white cell assay on the blood analyzer using in vitro human samples spiked with fluorescently labeled microbeads.

In this work, a synergy-based reinforcement learning algorithm has been developed to confer autonomous grasping capabilities to anthropomorphic hands. In the presence of high degrees of freedom, classical machine learning techniques require a number of iterations that increases with the size of the problem, thus convergence of the solution is not ensured. The use of postural synergies determines dimensionality reduction of the search space and allows recent learning techniques, such as Policy Improvement with Path Integrals, to become easily applicable. A key point is the adoption of a suitable reward function representing the goal of the task and ensuring one-step performance evaluation. Force-closure quality of the grasp in the synergies subspace has been chosen as a cost function for performance evaluation. The experiments conducted on the SCHUNK 5-Finger Hand demonstrate the effectiveness of the algorithm showing skills comparable to human capabilities in learning new grasps and in performing a wide variety from power to high precision grasps of very small objects.

This work describes how the localisation of autonomous underwater vehicles can be supported through networked acoustic communication. The localisation approach includes timing information within acoustic messages to create an interrogation scheme similar to that of long-baseline methods, but realised at the application level of the network. In this way, the network itself is able to provide vehicle localisation information, reducing the needs for additional on-board sensors or dedicated deployed platforms/transponders. The aim of this work is to report at sea localisation results as obtained in two completely different application scenarios. The first one is represented by the FP7 MORPH project (HORTA15 sea trial) where the proposed approach has been applied to support navigation of a fleet of AUVs in a tight formation and in very shallow waters. The second application is represented by the NATO STO CMRE multistatic network demonstrator with the acoustic network used to support navigation of AUVs working in large operational areas. In this latter case, results are given from the COLLAB-NGAS14 experimental campaign.