IROS 2019 论文列表

Human joint dynamic stiffness plays an important role in the stability of performance augmentation exoskeletons. In this paper, we consider a new frequency domain model of the human joint dynamics which features a complex value stiffness. This complex stiffness consists of a real stiffness and a hysteretic damping. We use it to explain the dynamic behaviors of the human connected to the exoskeleton, in particular the observed non-zero low frequency phase shift and the near constant damping ratio of the resonance as stiffness and inertia vary. We validate this concept with an elbow-joint exoskeleton testbed (attached to a subject) by experimentally varying joint stiffness behavior, exoskeleton inertia, and the strength augmentation gain. We compare three different models of elbow-joint dynamic stiffness: a model with real stiffness, viscous damping and inertia; a model with complex stiffness and inertia; and a model combining the previous two models. Our results show that the hysteretic damping term improves modeling accuracy (via a statistical F-test). Moreover, this term contributes more to model accuracy than the viscous damping term. In addition, we experimentally observe a linear relationship between the hysteretic damping and the real part of the stiffness which allows us to simplify the complex stiffness model down to a 1-parameter system. Ultimately, we design a fractional order controller to demonstrate how human hysteretic damping behavior can be exploited to improve strength amplification performance while maintaining stability.

Deep Reinforcement Learning (RL) has recently emerged as a solution for moving obstacle avoidance. Deep RL learns to simultaneously predict obstacle motions and corresponding avoidance actions directly from robot sensors, even for obstacles with different dynamics models. However, deep RL methods typically cannot guarantee policy convergences, i.e., cannot provide probabilistic collision avoidance guarantees. In contrast, stochastic reachability (SR), a computationally expensive formal method that employs a known obstacle dynamics model, identifies the optimal avoidance policy and provides strict convergence guarantees. The availability of the optimal solution for versions of the moving obstacle problem provides a baseline to compare trained deep RL policies. In this paper, we compare the expected cumulative reward and actions of these policies to SR, and find the following. 1) The state-value function approximates the optimal collision probability well, thus explaining the high empirical performance. 2) RL policies deviate from the optimal significantly thus negatively impacting collision avoidance in some cases. 3) Evidence suggests that the deviation is caused, at least partially, by the actor net failing to approximate the action corresponding to the highest state-action value.

Flexible and helical magnetic microswimmers have been well reviewed in the literature because they could be exploited for envisaged applications such as targeted drug delivery, material removal, and micromanipulation. In this article, scaled-up versions of those robots are introduced to study in detail their maneuverability and dexterity while swimming. The robots were immersed in pure glycerol, thus, reproducing a low Reynolds scenario. The proposed robots were previously optimized, achieving their best performances. The experiments assess the performances of these two kinds of robots in terms of rapidity, and steering error following 3D trajectories in environments with high viscous variations.

In this paper, we propose a novel compact reachability map representation for excavator motion planning. The constructed reachability map can concisely encode the bucket’s reachable pose and the translation capability limited by excavator’s kinematic structure. By explicitly exploiting the property that the basic excavation motion lies on the excavation plane determined by excavator links, we further reduce the construction of the map from 3D Euclidean space to 2D excavation plane. We show the pre-computed reachability map can be used to develop new excavator motion planning approach. By indexing on the pre-computed reachability map, we can efficiently compute the feasible full-bucket trajectory for single step excavation operation. We highlight the results of the reachability map construction and demonstrate the simulation results of motion planning using a commercial dynamic simulator.

Visual localization is one of the primary capabilities for mobile robots. Long-term visual localization in real time is particularly challenging, in which the robot is required to efficiently localize itself using visual data where appearance may change significantly over time. In this paper, we propose a cloud-based visual localization system targeting at long-term localization in real time. On the robot, we employ two estimators to achieve accurate and real-time performance. One is a sliding-window based visual inertial odometry, which integrates constraints from consecutive observations and self-motion measurements, as well as the constraints induced by localization results from the cloud. This estimator builds a local visual submap as the virtual observation which is then sent to the cloud as new localization constraints. The other one is a delayed state Extended Kalman Filter to fuse the pose of the robot localized from the cloud, the local odometry and the high-frequency inertial measurements. On the cloud, we propose a longer sliding-window based localization method to aggregate the virtual observations for larger field of view, leading to more robust alignment between virtual observations and the map. Under this architecture, the robot can achieve drift-free and real-time localization using onboard resources even in a network with limited bandwidth, high latency and existence of package loss, which enables the autonomous navigation in real-world environment. We evaluate the effectiveness of our system on a dataset with challenging seasonal and illuminative variations. We further validate the robustness of the system under challenging network conditions.

It has been widely considered that a distinctive feature of musculoskeletal structures is that both the joint angle and stiffness can be changed by exploiting the agonistantagonist driving of the joint. However, musculoskeletal systems in animals and humans are typically highly complex, and the simple agonist-antagonist driving is rarely found. Therefore, in accordance with the increasing complexity of musculoskeletal robots, the feature that causes the robot to assume a posture with different stiffness values becomes difficult to achieve, owing to the difficulty in modeling the kinematics. Although datadriven approaches such as the neural network are regarded as suitable for modeling complex relationships, the training data are difficult to obtain because measuring joint stiffness is typically extremely difficult in contrast to measuring an actuator's state and posture. Hence, we herein propose the common dimensional autoencoder where the encoded feature exhibits identical dimensions to the original input vector. In the proposed network, in parallel with the original unsupervised training using the data of the actuators' states, supervised training at part of the encoded features is performed using posture data. Consequently, features expressing the redundancy of inverse kinematics appear at the remaining part of the encoded features without using data such as joint stiffness. The validity of the proposed method was confirmed successfully through an experiment using a 10 degrees-of-freedom complex musculoskeletal robot arm driven by pneumatic artificial muscles.

Bio-inspired robots take advantage of millions of years of evolution to provide interesting and flexible solutions for issues related to motion and perception. Often, they have challenging kinematics classical robotics control mechanisms are not always able to take advantage of them. A concrete example of this is LAURON V, a six-legged robot for space exploration inspired by the stick insects. The main goals of this work is to combine classical behaviour-based control with motor primitives implemented with SNN for motion representation. We extend a previously presented bio-inspired approach to represent hand and arm motion using motor primitives, and combine it with a behaviour-based architecture to model different locomotion behaviours for a multi-legged robot. There are four main components. First, to model the individual leg motions we use two motor primitives implemented with spiking neural networks for the swing and stance phases. Second, to control the motor primitives of each leg there are local behaviours corresponding to each phase, and corresponding to each activation pattern. Third, the activation patterns are used to facilitate multi-leg coordination and generate different walking behaviours. Fourth, a high-level control interface integrates control signals from other sources and activates the patterns. We conducted five different experiments to evaluate our approach in a simulated environment using the Neurorobotics Platform (NRP). The results show that our modelling approach with motor primitives is flexible enough to represent different types of motions, and also highlight the value of the NRP for robotics development.

This paper addresses the problem of exploring unknown terrains with a fleet of cooperating aerial vehicles. We present a novel decentralized approach which alternates gradient-free stochastic optimization and a frontier-based approach. Our method allows each robot to generate its trajectory based on the collected data and the local map built integrating the information shared by its teammates. Whenever a local optimum is reached, which corresponds to a location surrounded by already explored areas, the algorithm identifies the closest frontier to get over it and restarts the local optimization. Its low computational cost, the capability to deal with constraints and the decentralized decision-making make it particularly suitable for multi-robot applications in complex 3D environments. Simulation results show that our approach generates feasible trajectories which drive multiple robots to completely explore realistic environments. Furthermore, in terms of exploration time, our algorithm significantly outperforms a standard solution based on closest frontier points while providing similar performances compared to a computationally more expensive centralized greedy solution.

Learning from demonstrations is a promising paradigm for transferring knowledge to robots. However, learning mobile manipulation tasks directly from a human teacher is a complex problem as it requires learning models of both the overall task goal and of the underlying actions. Additionally, learning from a small number of demonstrations often introduces ambiguity with respect to the intention of the teacher, making it challenging to commit to one model for generalizing the task to new settings. In this paper, we present an approach to learning flexible mobile manipulation action models and task goal representations from teacher demonstrations. Our action models enable the robot to consider different likely outcomes of each action and to generate feasible trajectories for achieving them. Accordingly, we leverage a probabilistic framework based on Monte Carlo tree search to compute sequences of feasible actions imitating the teacher intention in new settings without requiring the teacher to specify an explicit goal state. We demonstrate the effectiveness of our approach in complex tasks carried out in real-world settings.

Vision systems are often used jointly with robotic manipulators to perform automated tasks in industrial applications. Still, the correct set up of such workcells is difficult and requires significant resources. One of the main challenges, when implementing such systems in industrial use cases, is the pose uncertainties presented by the vision system which have to be handled by grasping. In this paper, we present a framework for the design and analysis of optimal gripper finger designs and vision parameters. The proposed framework consists of two parallel methods which rely on vision and grasping simulation to provide an initial estimation of the uncertainty compensation capabilities of the designs. In case the compensation is not feasible with the initial design, an optimization process is introduced, to select the optimal pose estimation parameters and finger designs for the presented task. The proposed framework was evaluated in dynamic simulation and implemented in a real industrial use case.

As robotic systems become more flexible and intelligent, they must be able to move into environments with a high degree of uncertainty or clutter, such as our homes, workplaces, and the outdoors. In these unstructured scenarios, it is possible that the body of the robot collides with its surroundings. As such, it would be desirable to characterise these contacts in terms of their location and interaction forces. This paper addresses the problem of detecting and isolating collisions between a robotic manipulator and its environment, using only on-board joint torque and position sensing. The algorithm is based on a particle filter and, under some assumptions, is able to identify the contact location anywhere on the robot body. It requires the robot to perform small exploratory movements, progressively integrating the new sensing information through a Bayesian framework. The approach was tested and benchmarked in simulation, with respect to its accuracy and robustness. Validation using a robot with joint torque sensing in a real environment demonstrated the applicability of the method to real-world scenarios.

Collaborative robotics refers to the cooperation between humans and machines and aims at improving productivity and at facilitating the worker in demanding tasks. The advantage of collaboration is to combine the superior cognitive and motor skills of the operator with the physical capabilities of the robots. This work presents a control strategy for the robotic manipulator to minimise the muscular fatigue of the human operator during the manipulation of bulky objects. The robot moves the workpiece so that the human is always operating close to his/her most natural and ergonomic posture. This way the risk of developing postures and movements inducing musculoskeletal disorders is minimised. A substantial reduction of the amplitude of the operator movements, without degrading the precision in fulfilling the task, has been registered in the experimental campaign.

Many robotic applications, especially exploration scenarios, benefit from deploying multiple collaborating robots with the aim of parallelizing and therefore accelerating the involved task. One critical part of a multi-robot system is its communication system. Depending on the application scenario, high-bandwidth wireless connections, such as WiFi, may not always be available and suffer from a limited communication range. On the other hand, low-bandwith systems require the application itself to deal with limited information exchange. In this work, we present a novel approach for collaborative mapping using mixtures of occupancy and NDT maps (called ONDT), which provide detailed information at low resolutions and in which the pose uncertainty can be encoded efficiently. Further, we compare the applicability of three different radio frequency modules operating at different frequencies in real world experiments with five robots at large distances.

In this paper, we are proposing a collaborative SLAM system between a team of three heterogeneous agents: a robot, a human operator, and an augmented reality head mounted display (ARHMD). The system allows for online editing of a map produced by a robot running SLAM. Through hand gestures, the user can edit, in real time, the robot map that is augmented on top of the physical environment. Moreover, the proposed system leverages the built-in SLAM capabilities of the AR-HMD to correct the robot's map and map areas that are not yet discovered by the robot. Our method aims to combine the unique and complementary capabilities of each of the three different agents to produce the maximum possible mapping accuracy in the minimum amount of time. The proposed system is implemented on ROS and Unity. Experiments performed demonstrate the considerably superior SLAM outputs in terms of reducing mapping time, eliminating maps post-processing, and increasing mapping accuracy.

The development of robotic systems with a certain level of autonomy to be used in critical scenarios, such as an operating room, necessarily requires a seamless integration of multiple state-of-the-art technologies. In this paper we propose a cognitive robotic architecture that is able to help an operator accomplish a specific task. The architecture integrates an action recognition module to understand the scene, a supervisory control to make decisions, and a model predictive control to plan collision-free trajectory for the robotic arm taking into account obstacles and model uncertainty. The proposed approach has been validated on a simplified scenario involving only a da VinciO surgical robot and a novel manipulator holding standard laparoscopic tools.

Robotic arms can perform grasping actions thanks to their “dexteorus” part, i.e. the gripper. Among the various categories, nowadays pneumatic grippers became the most employed in industry, as they have low cost and little bulkiness. Despite their simplicity, controlling the force applied by these grippers is not straightforward due to the dependence of such a force on the air pressure in the gripper chambers. As a result, it is still tricky to implement closed-loop force control for pneumatic grippers. This paper intends to deliver a control scheme relying on the force measurement to control pneumatic grippers. The force might be measured through a commercial sensor (e.g. a load cell) and fed back to close the control loop. This includes a calibration which maps the force-pressure relation taking into account both desired force and length of the gripper fingers. The control scheme exploits two different pressure regulators to precisely adjust the air pressure inside the gripper chambers (i.e. opening and closing chambers). To this aim, a quadratic programming algorithm is employed. The control scheme performance revealed to be good: results will be shown in terms of gripper response to sinusoidal and step inputs, along with the pressure-force characterization.

Compared with conventional robots, soft structures such as living octopus arms and various soft-robot arms have more degrees of freedom (DOFs) and greater flexibility. Soft robot arms have a considerable range of applications. However, it is arduous to establish a mechanical model for them, because of the hyper-redundant DOFs, and the hyperelasticity and nonlinearity of the soft material. In this study, to investigate the deformation of soft octopus robot arms, the simplified closed-form analytical equations for the curvature and torsion were derived according to the Cosserat theory. A closed-form model for axial constriction was developed. The analytical equations were experimentally validated, and a dynamical simulation of the multi-flexible bodies was performed for a cable-driven soft-robot arm inspired by the octopus. The results show satisfactory accuracy.

In this paper, we propose SwarmNet – a neural network architecture that can learn to predict and imitate the behavior of an observed swarm of agents in a centralized manner. Tested on artificially generated swarm motion data, the network achieves high levels of prediction accuracy and imitation authenticity. We compare our model to previous approaches for modelling interaction systems and show how modifying components of other models gradually approaches the performance of ours. Finally, we also discuss an extension of SwarmNet that can deal with nondeterministic, noisy, and uncertain environments, as often found in robotics applications.

People are not perfect, and if given the chance, some will be dishonest with no regrets. Some people will cheat just a little to gain some advantage, and others will not do it at all. With the prospect of more human-robot interactions in the future, it will become very important to understand which kind of roles a robot can have in the regulation of cheating behavior. We investigated whether people will cheat while in the presence of a robot and to what extent this depends on the role the robot plays. We ran a study to test cheating behavior with a die task, and allocated people to one of the following conditions: 1) participants were alone in the room while doing the task; 2) with a robot with a vigilant role or 3) with a robot that had a supporting role in the task, accompanying and giving instructions. Our results showed that participants cheated significantly more than chance when they were alone or with the robot giving instructions. In contrast, cheating could not be proven when the robot presented a vigilant role. This study has implications for human-robot interaction and for the deployment of autonomous robots in sensitive roles in which people may be prone to dishonest behavior.