IROS 2018 论文列表

The 2018 IROS Fan Robotic Challenge tasked participants with programming a robot to autonomously open and close a Spanish folding fan, highlighting the obstacles still associated with the dexterous manipulation of objects for robotic systems. Since high DoFs grippers are complex to coordinate and overkill for many industrial processes, our approach used an under-actuated parallel gripper with a 3D-printed adaptation to precisely grasp the fan in such a manner that gravity could be leveraged to act on the fan to produce an extrinsic, or external, dexterity. With our approach, we completed the challenge in 12.38 seconds, resulting in a top three finish. Furthermore, using a multi-modal tactile sensor, we analyzed the vibrations in the grasp during the manipulation and were able to distinguish the opening and closing of the fan from the motion of the robot with a 83% accuracy.

In this work we propose a Bayesian User Model which is able capture a unified representation of cultural attributes from heterogeneous information in the context of Human-Robot Interaction. Despite the latest advances in robotic technologies, virtually no robots are able to cope with the specificities of the “modus vivendi” of different cultures. We start by proposing Bayesian classifiers to capture unitary attributes of different users, clustering them in a n-dimensional semantic attribute space, aggregating groups of persons that share similar attributes. Results show a highly accurate classification framework, both capable of detecting specific subtleties in user's properties, and generalizing them into representative profiles. We then discuss its application towards adapting the actions of a robot and its potential impact on culture-awareness, demonstrating how the proposed framework can enable culture-awareness, exploring this new frontier in social robotics.

To enable robots to work on real home environments, they have to not only consider common knowledge in the global society, but also be aware of existing rules there. Since such “local rules” are not describable beforehand, robot agents must acquire them through their lives after deployment. To achieve this, we developed a framework that a) lets robots record long-term episodic memories in their deployed environments, b) autonomously builds probabilistic object localization map as structurization of logged data and c) make adapted task plans based on the map. We equipped our framework on PR2 and Fetch robots operating and recording episodic memory for 41 days with semantic common knowledge of the environment. We also conducted demonstrations in which a PR2 robot tidied up a room, showing that the robot agent can successfully plan and execute local-rule-aware home assistive tasks by using our proposed framework.

Social robots able to continually learn facial expressions could progressively improve their emotion recognition capability towards people interacting with them. Semi-supervised learning through ensemble predictions is an efficient strategy to leverage the high exposure of unlabelled facial expressions during human-robot interactions. Traditional ensemble-based systems, however, are composed of several independent classifiers leading to a high degree of redundancy, and unnecessary allocation of computational resources. In this paper, we proposed an ensemble based on convolutional networks where the early layers are strong low-level feature extractors, and their representations shared with an ensemble of convolutional branches. This results in a significant drop in redundancy of low-level features processing. Training in a semi-supervised setting, we show that our approach is able to continually learn facial expressions through ensemble predictions using unlabelled samples from different data distributions.

This paper presents an approach to generate the time-optimal trajectory for a robot manipulator under certain kinematic constraints such as joint position, velocity, acceleration, and jerk limits. This problem of generating a trajectory that takes the minimum time to pass through specified waypoints is formulated as a nonlinear constraint optimization problem. Unlike prior approaches that model the motion of consecutive waypoints as a Cubic Spline, we model this motion with a seven-segment acceleration profile, as this trajectory results in a shorter overall motion time while staying within the bounds of the robot manipulator's constraints. The optimization bottleneck lies in the complexity that increases exponentially with the number of waypoints. To make the optimization scale well with the number of waypoints, we propose an approach that has linear complexity. This approach first divides all waypoints to consecutive batches, each with an overlap of two waypoints. The overlapping waypoints then act as a bridge to concatenate the optimization results of two consecutive batches. The whole trajectory is effectively optimized by successively optimizing every batch. We conduct experiments on practical scenarios and trajectories generated by motion planners to evaluate the effectiveness of our proposed approach over existing state-of-the-art approaches.

Gas pipeline requires to be inspected regularly for leakages caused by natural disaster. Robots are widely used for pipeline inspection since they are more convenient than manual inspection. Several problems, however, exist due to the restriction by complex pipe networks. The most significant one is limited inspection range caused by restriction of cable length or wireless signal attenuation. In this paper, we proposed a concept of wireless relay communication to assist robot to extend the inspection range, and we newly developed a tracked robot chain system. In this system, each robot serves as a relay communication node. Leakage information of pipes are transmitted via these relay nodes. To ensure the stability of relay communication between adjacent robots, we adopted RSSI (received signal strength indication)-based evaluation method for cooperative and coordinated movement of robot chain system. Moreover, wireless application layer communication protocol (WALCP) was used to increase the stable performance of wireless relay communication. Each robot can self-navigate based on distance measurement module, which enables robots to pass through an elbow junction. Multiple experiments to evaluate relay transmission efficiency, RSSI-based cooperative movement, and comprehensive performance were conducted. Results revealed that our proposed system could realize relatively accurate relay transmission and RSSI-based coordinated movement.

This paper addresses the problem of assist-as-needed (AAN) control for rehabilitation robots. To achieve a motion which is not explicitly a function of time, the velocity field control is considered in this paper. The proposed new controller consists of a proportional-like feedback term and a neural network (NN) term, where the later is exploited to compensate for the dynamic uncertainties of the system. The AAN property is facilitated by means of a dead-zone function in the feedback control term and a forgetting factor in the adaptation law of NN component. The designed controller guarantees the stability of the system with a bounded control command. The performance of the proposed AAN scheme is validated through the simulation and experiment conducted on a lower-limb exoskeleton.

Quadrupedal trotting gaits of constant forward velocity and body height are studied. A method is developed, which is structured upon analytical expressions derived from the dynamics of a reduced single-legged model comprised of a point mass, and two actuated rotational joints. The inputs of the method include the robot mass, the leg and actuator properties, and the desired forward velocity, yielding all robot body feasible trajectories and their energy footprints. Thus, the method predicts the maximum forward velocity of a trotting quadruped; it also suggests energetically optimal combinations of body height and step length for a given forward velocity.

Typically, the range and sensitivity of force sensors are determined during production. However, to be able to do both delicate and high-force demanding work, adjustable force sensitivity would be beneficial. The current paper proposes such a sensor by implementing a planar electromagnet above a 3-axis magnetic sensor, separated by soft foam. Furthermore, the sensor has digital output with an integrated microcontroller. The magnetic field strength with varying currents is examined in simulation, and the field changes according to displacements are investigated both in simulation and with the actual sensor. A prototype 3-axis force sensor is implemented and the relationship between the magnetic field change and the corresponding applied force is also investigated. It could be shown that the sensitivity of the sensor to displacements, as well as force, can indeed be adjusted.

This paper develops an adaptive gripper for peg-in-hole tasks. Conventional grippers require complicated compliant mechanisms or complicated control strategy and force sensing to successfully insert pegs into holes. Different from them, this paper proposes a simple gripper with an L-shape finger as a low-cost peg-in-hole solution. The basic idea is to divide a peg-in-hole process into a preparation phase and an execution phase, and eliminate uncertainty step-by-step by pushing using the L-shape finger in the preparation phase. The robustness of the gripper for peg-in-hole tasks is examined by repeated executions for different pegs in the International Robotic Exhibition 2017 (IREX) in Tokyo. The experimental section presents details of the executions, and qualitatively shows the high performance of the proposed gripper.

A new approach for cellular robots is presented. The single elements of the robot are triangular cells, which can change their shape by means of linear actuators at each edge. The novelty concerns the connection of autonomous cells at their edges rather than at the vertices. In this way, unstructured triangular meshes can be formed. The robot can self-reconfigure and thus can reproduce almost arbitrary planar shapes. In a similar way, the system has been realized with tetrahedrons in a simplified way within a previous work. The self-reconfigurable system shall serve as a basis for programmable matter. The present paper includes the mechatronic design, its components and the kinematic model of the cellular robot. In order to reduce positioning errors, a model is developed, which considers compliance and clearance in the links and joints. Based on a simplified mechanical model using elastic trusses, the positioning errors can be predicted. The parameters of these models are identified from simple motion sequences. Furthermore, the nonlinearity of actuators is identified and corrected. In this way, the desired triangular shapes can be prescribed without measuring the position of the cells.

Conventional skid or wheel based helicopter landing gears severely limit off-field landing possibilities, which are crucial when operating in scenarios such as mountain rescue. In this context, slopes beyond 8° and small obstacles can already pose a substantial hazard. An adaptive landing gear is proposed to overcome these limitations. It consists of four legs with one degree of freedom each. The total weight was minimized to demonstrate economic practicability. This was achieved by an innovative actuation, composed of a parallel arrangement of motor and brake, which relieves the motor from large impact loads during hard landings. The loads are alleviated by a spring-damper system acting in series to the actuation. Each leg is individually force controlled for optimal load distribution on compliant ground and to avoid tipping. The operation of the legs is fully autonomous during the landing phase. A prototype was designed and successfully tested on an unmanned helicopter with a maximum take-off weight of 78 kg. Finally, the implementation of the landing gear concept on aircraft of various scales was discussed.

This paper first presents a formula to predict the largest balance disturbance from which a legged robot can recover without taking a step. It then presents an actuator design criterion derived from this formula that maximizes the robot's ability to recover. In this study, it is assumed that the robot is using a single major joint (e.g, a hip joint) to perform its balance recovery movement, and that the actuator consists of an electric motor and reduction gear. It is also assumed that the robot's support polygon is sufficiently small that it can be approximated as a point, and that the balance recovery motion is essentially planar, so that a 2-D analysis remains valid in 3-D. Finally, it is assumed that, for the purpose of studying balance recovery motion, the robot can be approximated by a reaction wheel pendulum. The theory has been tested experimentally on a robot designed to be good at balancing, and was found to agree closely with experimental results.

Cable-Driven Parallel Robots (CDPRs) can execute fast motions across a large workspace. However, these performances are reached at the cost of a relatively low stiffness which often yields parasitic vibrations at the CDPR mobile platform. In this paper, vibration damping of CDPRs is addressed by means of an original active stabilizer consisting of actuated rotating arms installed on-board the CDPR mobile platform. A control strategy for the whole system, which consists of the CDPR and the stabilizer, and with one purpose for each-position control for the platform and vibration damping for the stabilizer-is designed. The system being controlled at two different time scales, the singular perturbation theory can be used to prove the stability of the corresponding closed-loop system. The efficiency of the proposed device and control strategy is tested in simulations in the case of a planar 3-DOF CDPR equipped with a three-arm stabilizer.

In this paper, we present algorithms for synthesizing controllers to distribute a swarm of homogeneous robots (agents) over heterogeneous tasks which are operated in parallel. Swarm is modeled as a homogeneous collection of irreducible Markov chains. States of the Markov chain represent the tasks performed by the swarm. The target state is a pre-defined distribution of agents over the states of the Markov chain (and thus the tasks). We make use of ergodicity property of irreducible Markov chains to ensure that as an individual agent converges to the desired behavior in time, the swarm converges to the target state. To circumvent the problems faced by a global controller and local/decentralized controllers alone, we design a controller by combining global supervision with local-feedback-based state level decisions. Some numerical experiments are shown to illustrate the performance of the proposed algorithms.

Vehicles with car-like kinematics are ubiquitous, therefore an ability to algorithmize (i.e., how to plan and effectively execute) complex maneuvers in the presence of obstacles is vital to mobile robotics and intelligent vehicles. Traditionally, this problem is solved using the well known motion planning algorithms, which generate the open-loop control signals neglecting the effects of measurement noises, modeling uncertainties and imperfect robot actuation. While such effects can be compensated to some extent by online replanning, the application of feedback control algorithms to motion execution is unavoidable if robustness of the system is desired. Consequently, the recent works focus on integration of both motion planning and control algorithms to obtain motion plans robust to uncertainty of the initial conditions. In accordance with this trend, we propose a modified VFO (Vector Field Orientation) control law, which is designed to satisfy the state and input constraints resulting from the presence of obstacles in the environment, respect the steering angle limits in conjunction with steering dynamics of the car-like robot, and preserve continuity of the control input signals. Thanks to analytic characterization of admissible funnels (i.e. positively invariant subsets of the configuration space) developed from an analysis of the VFO control law, we guarantee satisfaction of all the mentioned constraints in the continuous domains of time and configuration space of the robot without sacrificing computational efficiency of the planning process. A specific funnel is planned with a highly parallelized deterministic sampling-based algorithm achieving quasi-real-time performance.

We have proposed airborne docking using two multi-rotor aerial robots. This paper presents a transport multi-rotor UAV with winch mechanism and a small multi-rotor with onboard locolization and mobile manipulation system. The winch mechanism enables the UAV to lower and raise a bar to transport another UAV attached to it. The airborne docking method used in our work is chosen in order to avoid the effect of downwash generated by the multi-rotors. With experiments we have verified the possibility of airborne docking, and evaluated how it influences the transport multi-rotor UAV as the load is changed, using the IMU data of UAV.

We propose and test an autonomous robot behavior for socially-compliant navigation of doorways with both human and robot interlocutors. Building on previous work for “aggressive” interaction between robots to resolve navigation deadlocks in corridors, we demonstrate an “assertive” robot that negotiates right-of-way when faced with a human or other robot. The negotiation is implemented using only motion and common navigation sensors, without explicit message-passing. Our goal is for the correct agent to take priority, as decided both by time-efficiency and as judged subjectively by naive human participants. Our contribution is a practical method for doorway negotiation, and a study of human users' responses to a robot that appears to participate in existing social customs surrounding doors. Our method is evaluated with robot-robot experiments and a human-robot interaction study with nonexpert users.

Affordances provide a natural means for a robot to describe its agency as actions it can perform on objects. Further, affordances can enable robots to reason complicated, multi-step tasks that involve proper use of a diversity of objects. This paper proposes the concept of affordance wayfields for representing manipulation affordances as objective functions in configuration space. Affordance wayfields quantify how well a path, or sequence of motions, will accomplish an afforded action on an object. Paths that enact affordances can be located by performing a randomized form of gradient descent over affordance wayfields. Incorporating obstacles, or other constraints into wayfields allows our method to adaptively generate valid motions for executing afforded actions. We demonstrate that affordance wayfields can enable robots, such as the Michigan Progress Fetch mobile manipulator, to solve complex real-world tasks such as assembling a table, or loading and unloading objects from a storage chest.