ICRA 2017 论文列表

Use of robots is rising in process applications where robots need to interact with parts using tools. Representative examples can be cleaning, polishing, grinding, etc. These tasks can be non-repetitive in nature and the physics-based models of the task performances are unknown for new materials and tools. In order to reduce operation cost and time, the robot needs to identify and optimize the trajectory parameters. The trajectory parameters that influence the performance can be speed, force, torque, stiffness, etc. Building physics-based models may not be feasible for every new task, material, and tool profile as it will require conducting a large number of experiments. We have developed a method that identifies the right set of parameters to optimize the task objective and meet performance constraints. The algorithm makes decisions based on uncertainty in the surrogate model of the task performance. It intelligently samples the parameter space and selects a point for experimentation from the sampled set by determining its probability to be optimum among the set. The iterative process leads to rapid convergence to the optimal point with a small number of experiments. We benchmarked our method against other optimization methods on synthetic problems. The method has been validated by conducting physical experiments on a robotic cleaning problem. The algorithm is general enough to be applied to any optimization problem involving black box constraints.

We present a data-driven imitation learning system for learning human-robot interactions from human-human demonstrations. During training, the movements of two interaction partners are recorded through motion capture and an interaction model is learned. At runtime, the interaction model is used to continuously adapt the robot's motion, both spatially and temporally, to the movements of the human interaction partner. We show the effectiveness of the approach on complex, sequential tasks by presenting two applications involving collaborative human-robot assembly. Experiments with varied object hand-over positions and task execution speeds confirm the capabilities for spatio-temporal adaption of the demonstrated behavior to the current situation.

This paper offers a novel insight of using nonlinear models for the control to produce more robust and natural walking gaits for humanoid robots. The sagittal and lateral gait control needs to be treated differently, hence, we proposed two types of suitable nonlinear models, which allow forward simulations to look ahead, and thus, predict accurately the future trajectory/state at the end of the current step. Subsequently, by performing multiple forward simulations in a similar manner for the next step and using the gradient descent method, an appropriate foot placement can be found to achieve precise walking speed. By doing this two-step lookahead, all trajectories of the support and the swing leg can be generated. Our proposed controller can plan trajectories at the beginning of each step or actively re-plan according to task state errors. It is validated effectively in simulations performed in both ADAMS and Open Dynamic Engine. The robot can successfully traverse up/down a stair and recover from pushes with more natural looking gaits compared to the conventional bent-knee style. The reasonable computational time also indicates the feasibility of real-time implementation on real robots.

The addition of manipulation capabilities to telepresence robots holds the promise of enabling remote humans to perform tele-labor, hands-on training, and collaborative manipulation, but the use of a robot as a mediator to humanhuman physical interaction is not yet well understood. This paper studies the impact of telepresence modalities in the context of robot-mediated object handover. A teleoperation system was developed involving a bimanual mobile manipulator with telepresence head and sensing capabilities, and a user study was conducted with n=10 pairs of subjects under a variety of audio and visual telepresence conditions. Results show that telepresence does not significantly affect objective handover fluency, but both audio and video telepresence do significantly improve user experience on subjective measures including intimacy and perceived fluency.

This paper proposes a non-dimensional representation for hydraulic arms whose original representation is complex in terms of the nonlinear dynamics and many physical parameters. Unlike the usual nondimensional representations, the proposed nondimensional representation preserves a parametric structure in the original representation. Without loss of generality, only by changing the damping constant, the rod area, the source pressure, and the cylinder allocation, and also assuming that all the other parameters are unit, any numerical property such as the numerical existence is investigated efficiently.

This paper reports a novel stable adaptive attitude estimator and preliminary simulation results of a true-North gyrocompass system employing the attitude adaptive identifier and a commercially available low-cost inertial measurement unit (IMU) comprising a 3-axis fiber optic gyroscope (FOG) with a 3-axis micro-electro-mechanical systems (MEMS) accelerometer. Optical North-seeking gyrocompass systems typically employ a microprocessor system to sample the low-level raw sensor values for angular-rate and linear-acceleration at a high sampling rate and estimate true-North heading, pitch, and roll. This paper reports the first adaptive attitude estimator on SO (3) which utilizes 3-axis angular-rate sensor data and 3-axis linear acceleration sensor data to estimate the instrument's 3-degrees of freedom (DOF) attitude (roll, pitch, and heading) without using magnetometry of the Earth's magnetic field. A stability proof and preliminary numerical simulation results are reported. The simulation results for a rotating IMU configuration are promising, and further experimental evaluation and extension of the algorithm for the case of a translating IMU configuration typically found on moving robotic vehicles are needed.

In this paper, a new robust position controller is proposed for Series Elastic Actuators (SEAs) by using Sliding Mode Control (SMC) and a second order Disturbance Observer (DOb). The latter estimates not only disturbances but also their first and second order successive derivatives. A simple yet efficient dynamic model of the position control system is derived by using the analogy of a two-mass-spring-damper system. It is of fourth order and suffers from collocated and non-collocated disturbances. The former is directly cancelled by feeding-back its estimation through control input. The latter is suppressed by treating the estimations of disturbances and their first and second order time derivatives in the design of the SMC-based robust position controller. By cancelling disturbances via their estimations, not only the robustness of the position control system is improved but also the control signal chattering is lowered. The proposed robust controller significantly improves the position control performance of SEAs by suppressing plant uncertainties and external disturbances, such as friction, backlash, inertia variation and load. The validity of the proposed robust position controller is verified by giving experimental results of an SEA.

This study proposes a self-locking-type expansion mechanism for in-pipe robots. Previously, we proposed a highspeed locomotion mechanism using pneumatic hollow-shaft actuators; however, this mechanism lacked holding force and could not pass through a bent pipe. The proposed mechanism generates a large holding force and can easily pass through a bent pipe by invoking a self-locking phenomenon. We conceptualize and design the novel expansion mechanism and introduce its associated mathematical model to formulate the holding force and mechanism design. The characteristics and capabilities of the mechanism are elucidated by experiments. From the experimental results, we optimize the applied pressure and the design of the mechanism. The proposed mechanism generates a maximum holding force of 69.7 N, which is 5.2 times higher than that of the previous mechanism, and drastically improves the robot's bent-pipe-passing capability. Finally, the performance of this mechanism is confirmed in a simulated pipe test. In this trial, a robot equipped with the proposed mechanism smoothly and steadily moves through complex pipe configurations, including the vertical and bent pipes.

Despite the growing focus on the design of compliant mechanisms for robotics actuators that manifest several advantages in terms of robustness and interaction-related characteristics, the incorporation of elasticity in the actuation drive renders under-damped vibration modes and reduces the bandwidth of the system. The addition of damping principles into compliant systems can address such impediments to accuracy and stability, and enhance the passivity characteristics of the controlled compliant actuator. However, passive damping mechanisms integrated into compliant systems to exhibit user-defined passive dissipation profiles have not been realized. This paper proposes a non-linear stiffness compliant module, and introduces a novel non-linear damper which complements the elastic element. The cam-follower mechanism was employed for rendering the user-defined non-linear behaviour. While the passive compliance of the module is replicated using a curved leaf spring, the passive damping is generated by rolling/sliding motion of a rigid cylinder on an elastomer. The design of the module is described, the theoretical modelling is presented, and experimental results validating the functionality of the proposed design in dissipating under-damped oscillations are demonstrated.

Magnetic resonance imaging (MRI) offers many benefits, including unsurpassed soft-tissue characterization and the ability to combine detection and biopsy into a single procedure. However, limited patient access in the narrow scanner bore requires tedious iterative positioning or use of robotic assistants that isolate the physician from the patient. As an alternative, we present a teleoperation technology for percutaneous procedures to meet the needs of interventional radiologists and overcome challenges imposed by the MR environment. The technology is demonstrated for a 1-DOF needle insertion procedure. The technology uses rolling diaphragms, a clutch, and a cable-capstan drive to propel the needle while relaying forces and motions to the operator. The system demonstrates excellent position tracking (< 0.7° error in the unloaded case) and reliably transmits changes in force. During needle teleoperation, users were able to detect light membrane punctures and differentiate spring stiffnesses nearly as accurately as by hand manipulation.

Reinforcement learning has become more and more popular in robotics for acquiring feedback controllers. Many approaches aim for learning a controller from scratch, i.e., data-driven without any modeling of the physical plant. However, stability properties of the closed loop are often not considered, or established only a-posteriori or ad hoc. We propose to employ reinforcement learning in the context of model-based control, allowing to learn in a framework of stabilizing controllers built by using only little prior model knowledge. This way, the action space is suitably structured for safe learning of a feedback controller to compensate for uncertainties due to model mismatch or external disturbances. The resulting scheme is developed around a decentralized PD feedback controller. Therefore, given such a controller, by the proposed method one can also add a learning module for performance enhancement. We demonstrate our approach both in simulation and in a hardware experiment using a two degree of freedom robot manipulator.

Electromagnetically actuated microparticles can be widely applied in the field of biomedicine, for its advantages of minimally invasive feature and approachability to complex microenvironments. In this paper, we propose a robust feedback control approach for precise 3D manipulation of a microparticle actuated by a self-constructed electromagnetic coil system. Model uncertainties, environmental disturbances as well as actuator energy loss problem are all taken into account in the controller design. It is shown that this proposed control scheme can enable the entire system to maintain the input-to-state stability in presence of various perturbations. Experimental results have demonstrated the effectiveness of the proposed control approach. Success of the current study will benefit the precise motion control with high throughput in applications of the targeted material delivery.

Robotic orthoses have potential to assist people having difficulty in walking due to their neurological disorders. However, it is important to design lighter orthoses since additional weight and inertia from the device cause discomfort to the wearer and even instability during walking in some extreme cases. To address this problem, a robotic orthosis with a cable differential mechanism is proposed in this paper. It is designed to assist stroke patients with hemiplegia. It has 2 active degrees of freedom at the hip and knee joints and one passive degree of freedom at the ankle. A cable differential mechanism is used to transmit the torques generated by the actuators, which are located near the pelvis of the wearer to reduce the inertial effect. The cable differential mechanism allows for the actuators to share the load with each other, which results in decrease of the maximum required torques by the actuators. Therefore, smaller actuators are possible to be used for further reduction of the weight. The proposed robotic orthosis with a cable differential mechanism, which is called “COWALK-Mobile 2,” is implemented and evaluated.

Soft robots are inherently compliant and adaptive, therefore they are promising candidates for interacting with humans. However robotic manipulators utilizing soft actuators are often constrained by a series of actuator performance limitations. In this work we design a novel linear soft robotic actuator with significantly improved performances over the existing products, achieving 300% deformation ratio, quasi-constant output force over a wide motion range, while maintaining passive compliance and adaptability. Moreover, the novel actuator is less prone to friction, and could be fabricated using inject molding and 3D printing, hence having high repeatability at very low cost. An analytical model was developed to characterize the actuator behavior and provide a guideline for actuator design according to performance specifications. A 6 DOF soft manipulator was designed and fabricated utilizing the novel soft actuator. The manipulator arm had a serial kinematic structure with a biomimetic wrist and was driven by 12 soft actuators mounted onto the arm links. With 1.2m workspace radius and 1kg payload, the working air pressure could be as low as 1bar. Preliminary results have shown the validity of the novel soft actuator and manipulator designs, as well as the strong potential of soft robots in human-oriented applications.

In this paper we present a novel approach to track and explore stiff tissues within 3-D ultrasound volumes acquired by a medical 3-D ultrasound probe mounted on a six degrees of freedom robotic arm. Autonomous palpation and on-line elastography process are implemented to estimate the elastic property of the tissues (strain) in a volume of interest (VoI) indicated by the user. The compression motion, required for the elastography, is performed by controlling the force applied by the ultrasound probe to the tissues. A visual servoing control for centering a rigid tissue (target) inside the field of view (FoV) of the ultrasound probe is established to always maintain the target visible. Additionally, rotations around the contact point between the tissue and the ultrasound probe are teleoperated through a haptic device handled by the user in order to allow exploration of the target surrounding areas. Results show a stable system that can be used in the future for diagnosis of diseases or tumor location.

Low back pain is one of the world's most serious health problems. Conservative methods are recommended for back pain, and stabilization exercise as one of these methods has been proven to be effective. The “big 3” exercises are proven stabilization exercises, and it is able to train most of the muscles associated with low back stability. However, they are hard to be performed by some patients because the big 3 require sufficient strength in the upper and lower limbs as well as in the low back to maintain their postures. In this paper, we propose a rehabilitation robot SERA (Stabilization Exercise Robot Assistance system) to compensate for this shortcoming, and we describe the robot's developments and experiments. The proposed robot is designed to achieve effects similar to the big 3. The robot also ensures active exercises by voluntary control of the exerciser and provides anti-gravity force generated by series elastic actuators (SEAs) in order to adjust the exercise load. Experiments using surface electromyograph (sEMG) sensors with three subjects show the results for these features.

Classical rigid-bodied robotic systems are presented with proven success in theoretical development and industrial applications, are recently challenged by the emergence of soft robotics due to a growing need in physical human-robot interactions (pHRI), such as wearable devices, medical robots, personal robots, etc. In this paper, we present the design and fabrication of a robust, hybrid bending actuator build from both rigid and soft components inspired by crustaceans, where its bending radius and axis can be mechanically programmed through the selective activation of the rigid exterior joints, actuated by the soft actuators inside. The hybrid actuator was experimentally measured in terms of bending and force tests to demonstrate the utility of this design. Finally, a case study was presented to demonstrate its capacity to adapt to specific objects geometry, anticipating its potential application in situations where compliance is the priority.

This paper presents a data-driven approach to model planar pushing interaction to predict both the most likely outcome of a push and its expected variability. The learned models rely on a variation of Gaussian processes with input-dependent noise called Variational Heteroscedastic Gaussian processes (VHGP) [1] that capture the mean and variance of a stochastic function. We show that we can learn accurate models that outperform analytical models after less than 100 samples and saturate in performance with less than 1000 samples. We validate the results against a collected dataset of repeated trajectories, and use the learned models to study questions such as the nature of the variability in pushing, and the validity of the quasi-static assumption.

Tracking is a common topic in various areas of robotics research. Motivated by the hunting behavior of predators in nature, we propose a prey-predator model for efficient robot tracking. The head direction and speed of the pursuer is automatically adjusted according to the position and velocity of the prey. Under the situation with perception uncertainty, where the actual location of the prey is not observable, the pursuer predicts the location of the prey according to simple inference, an online adaptive autoregressive model, or an online adaptive echo state network. Simulation results demonstrate that the proposed prey-predator model is able to control the pursuer and to track the prey efficiently, even under perception uncertainty. Simple inference gives better results when the motion of the target is piecewise linear, while echo state network is more suitable when the dynamics of the target are more complex. The proposed prey-predator model thus provides an efficient method tracking targets with various statistical nature of trajectories for applications such as underwater robot tracking, human tracking and team formation.