ICRA 2017 Papers

Although learning-based methods have great potential for robotics, one concern is that a robot that updates its parameters might cause large amounts of damage before it learns the optimal policy. We formalize the idea of safe learning in a probabilistic sense by defining an optimization problem: we desire to maximize the expected return while keeping the expected damage below a given safety limit. We study this optimization for the case of a robot manipulator with safety-based torque limits. We would like to ensure that the damage constraint is maintained at every step of the optimization and not just at convergence. To achieve this aim, we introduce a novel method which predicts how modifying the torque limit, as well as how updating the policy parameters, might affect the robot's safety. We show through a number of experiments that our approach allows the robot to improve its performance while ensuring that the expected damage constraint is not violated during the learning process.

Traditional approaches to simultaneous localization and mapping (SLAM) rely on low-level geometric features such as points, lines, and planes. They are unable to assign semantic labels to landmarks observed in the environment. Furthermore, loop closure recognition based on low-level features is often viewpoint-dependent and subject to failure in ambiguous or repetitive environments. On the other hand, object recognition methods can infer landmark classes and scales, resulting in a small set of easily recognizable landmarks, ideal for view-independent unambiguous loop closure. In a map with several objects of the same class, however, a crucial data association problem exists. While data association and recognition are discrete problems usually solved using discrete inference, classical SLAM is a continuous optimization over metric information. In this paper, we formulate an optimization problem over sensor states and semantic landmark positions that integrates metric information, semantic information, and data associations, and decompose it into two interconnected problems: an estimation of discrete data association and landmark class probabilities, and a continuous optimization over the metric states. The estimated landmark and robot poses affect the association and class distributions, which in turn affect the robot-landmark pose optimization. The performance of our algorithm is demonstrated on indoor and outdoor datasets.

For the robotically-assisted minimally invasive surgery, preoperative planning is essential towards assisting surgeons to prepare the intervention and to decide the best access to the surgical site. Many recent studies in preoperative planning have focused on the pose selection of the robot and the port placement. However, as such techniques cannot evaluate the performance of the multi-arm cooperation, their applications are constrained in real practise with multi-arm surgical robots. In this paper, the surgical workspace is divided and the subspaces are assigned with different weights to reflect the internal differences within the surgical workspace. We propose three metrics to evaluate the performance of the multi-arm surgical robot: Global Isotropy Index (GII) to measure the dexterity of one single robot arm; Cooperation Capability Index (CCI) to reflect the performance of the multi-arm cooperation; Minimum Distance Index (MDI) to describe the collision avoidance of the robotic arms. We also propose a combination of Particle Swarm Optimization (PSO) and Gaussian Process (GP) to locate the port placement and robot positioning. The proposed integrated PSO-GP-based optimization strategy is implemented on a three-arm surgical robot. Two sets of experiments are carried out to validate our method. The results demonstrate that the performance optimization strategy based on PSO-GP is capable of guiding surgeons to plan an intervention with the multi-arm surgical robot.

This work presents the preliminary experimental validation of a systematic prosthetic control strategy on a custom compliant transfemoral prosthesis with the end result being energy efficient 3-dimension (3D) multi-contact prosthetic walking. In particular, with the goal of capturing essential components of realistic amputee-prosthesis system, a 3D asymmetric hybrid system model is presented - this forms the foundation for formal gait design and control construction. Based on this model, a two-step direct collocation optimization method is utilized to design an energy efficient multi-contact prosthetic gait in 3D. The designed gaits are also subject to various practical constraints such as human-likeness constraints and comfortability constraints. For experimental validation, a 3D capable powered transfemoral prosthetic device is custom built so as to be amendable to realizing the designed 3D prosthetic gaits. Differentiating this device from existing powered prosthesis, compliant components are added to the three joints (two pitch joints and one roll joint) for the purpose of energy saving and human-like behaviors. Combining the presented control methodology and the novel hardware design, the end result is experimentally realized 3D multi-contact prosthetic walking with improved energy efficiency compared to other devices and control methods.

We present a novel method to learn human preferences during, and for, the execution of concurrent joint humanrobot tasks. We consider tasks realized by a team of a human operator and a robot helper that should adapt to the human's task execution preferences. Different human operators can have different abilities, experiences, and personal preferences, so that a particular allocation of activities in the team is preferred over another. We cast the behavior of concurrent multi-agent cooperation as a semi Markov Decision Process and show how to model and learn human preferences over the team behavior. After proposing two different interactive learning algorithms, we evaluate them and show that the system can effectively learn and adapt to human preferences.

Autonomous Mobility On Demand (MOD) systems can utilize fleet management strategies in order to provide a high customer quality of service (QoS). Previous works on autonomous MOD systems have developed methods for rebalancing single capacity vehicles, where QoS is maintained through large fleet sizing. This work focuses on MOD systems utilizing a small number of vehicles, such as those found on a campus, where additional vehicles cannot be introduced as demand for rides increases. A predictive positioning method is presented for improving customer QoS by identifying key locations to position the fleet in order to minimize expected customer wait time. Ridesharing is introduced as a means for improving customer QoS as arrival rates increase. However, with ridesharing perceived QoS is dependent on an often unknown customer preference. To address this challenge, a customer ratings model, which learns customer preference from a 5-star rating, is developed and incorporated directly into a ridesharing algorithm. The predictive positioning and ridesharing methods are applied to simulation of a real-world campus MOD system. A combined predictive positioning and ridesharing approach is shown to reduce customer service times by up to 29%. and the customer ratings model is shown to provide the best overall MOD fleet management performance over a range of customer preferences.

Robotic cardiac catheterization using ultrasound (US) imaging catheters provides real time imaging from within the heart while reducing the difficulty in manually steering a four degree-of-freedom (4-DOF) catheter. Accurate robotic catheter navigation in the heart is challenging due to a variety of disturbances including cyclical physiological motions, such as respiration. In this work we compensate for respiratory motion by using an Extended Kalman Filter (EKF) to predict target motion and by applying the predictions to steer the US imaging catheter. The system performance was measured in bench top experiments with phantom vasculature. The robotic system with predictive filtering tracked cyclically moving targets with 1.59 mm and 0.72° mean error. Accurately tracking moving structures can improve intra-procedural treatments and visualization.

The primary focus of this work is to examine how robots can achieve more robust sequential manipulation through the use of pre-touch sensors. The utility of close-range proximity sensing is evaluated through a robotic system that uses a new optical time-of-flight pre-touch sensor to complete a highly precise and sequential task - solving the Rubik's cube. The techniques used in this task are then extended to a more general framework in which ICP is used to match pre-touch data to a reference model, demonstrating that even simple pre-touch scans can be used to recover the pose of common objects that require sequential manipulation.

The paper presents a novel control method for the arm exoskeletons that takes into account the muscular force manipulability of the human arm. In contrast to classical controllers that provide assistance without considering the biomechanical properties of the human arm, we propose a control method that takes into account the configuration of the arm and the direction of the motion to effectively compensate the anisotropic property of the muscular manipulability of the human arm. Consequently, the proposed control method effectively maintains a spherical endpoint manipulability in the entire workspace of the arm. As a result, the proposed method allows the human using the exoskeleton to efficiently perform tasks in arm configurations that are normally unsuitable due to the low manipulability. We evaluated the proposed approach by a preliminary experimental study where a subject wearing a 2 DOF arm-exoskeleton had to move a 4 kg weight between several locations. The results of our study demonstrate that the proposed approach effectively augments the ability of human motor control to perform tasks equally well in the whole arm workspace that include configurations with low intrinsic manipulability.

A position-based proportional-derivative (PD) controller with inner torque feedback loops can be used as a simple controller to render compliant behaviors to hydraulic robots. However, using this control framework involves a tradeoff between the stability and performance of the closed-loop system (which includes the external environment) because the joint position sensors and control units (i.e., electrohydraulic servovalves) used in the control are separated (non-collocated) from the robot by their joint flexibility. To effectively overcome this limitation, this paper proposes a joint position-based PD control strategy for constructing an inherently stable and compliant hydraulic robot system. To this end, we use virtual internal leakage to separate the system by frequency into subsystems that include control units (i.e., servovalve), flexible joints, and robot manipulator, respectively. This architecture allows the hydraulic robot to behave as a passive system within its operating frequency region under the guidance of controllers designed to guarantee the stability of the passive subsystems within the respective frequency regions. The proposed approach was verified experimentally.

The purpose of this research is to present a new method to achieve precise position tracking control for robot finger with variable stiffness mechanism. First, the variable stiffness design of the finger which is actuated by SMA-3 fibers is presented. Then, the relationship between the variation of pulling force ΔF of the bending robot finger and input voltage of SMA-3 is established. In addition, the relationship between the pulling force F and the input voltage of SMA-2 wire is established as well. Therefore, a control method based on these models for the position tracking of robot finger with variable stiffness characteristics is proposed. The experimental results show that the proposed method has better performance than traditional PID control when the stiffness changed by heating current, resulting in a reduction of maximum error by 86%.

Wire-driven haptic devices can easily achieve highspeed operation because of the low inertia of light and thin wires. Therefore, it is expected to be widely used as a motion support system in fields such as sports training. However, usually these wires are driven by controlling each wire's tension using servo motors, which raises concerns about the safety in human-robot interaction. Thus, we propose to support the user by controlling servo brakes instead of motors, which can ensure safety. In this paper, we introduce a passive wire-driven system without any motors for realistic motion support in sports training. The system can measure the user motion and support the user while following a target form by a novel passive control method considering the orientation as well as the position using 7 wires' lengths and the brake tensions. We also conduct error evaluation experiments and show that a tennis beginner using this system can accurately follow the target form.

Minimally-invasive (MI) procedures are becoming more popular and frequent due to their benefits such as reduced patient trauma and hospitalization time. However, several common types of MI interventions are performed under X-ray guidance, which exposes both patients and staff to harmful ionizing radiation. Radiation exposure has therefore become a major concern for the medical community. Yet, few efforts to actively reduce it by exploiting the robotic capabilities of the devices present in the surgical suite have been performed. The propagation of radiation highly depends on the X-ray source positioning. Hence, we propose an approach to optimize the imaging device's pose in order to reduce the exposure to radiation of both patient and staff, while preserving the visibility of the targeted anatomical structure in the acquired image. Our method is based on the optimization of a cost function, which takes the current context and device parameters into account to compute the overall radiation exposure. It relies on GPU-accelerated Monte Carlo methods to simulate radiation propagation and performs the optimization in quasi real-time. When evaluated on a set of standard imaging configurations, our approach is able to recommend a device's pose in a few seconds, for which the delivered dose is reduced. Such an approach can contribute to lower the probability of appearance and severity of long-term negative effects due to radiation exposure and improve overall radiation safety.

In this paper we consider the problem in which the human commands the overall behavior of a robot team while the robots are controlled to comply with formation constraints. Such human-robot team interaction is challenging in terms of system complexity and control synthesis. Port-Hamiltonian framework is suitable for modeling the interconnected systems. In this paper we model the robotic team, cooperatively manipulating an object, as a constrained port-Hamiltonian system. Furthermore, we propose a passivity-based control approach in the port-Hamiltonian framework for the cooperative manipulation system guided by the human. The control mechanism is based on the energy shaping for achieving a desired behavior of the formation and its preservation. An energy tank in the cascade is introduced to guarantee passivity of the system commanded by the human and safe interaction with humans in the robot environment. We validate the proposed approach with simulation and experiments.

This paper presents a novel manufacturing paradigm for constructing origami-inspired pop-up robots for future space exploration missions. The new approach uses a textile-enhanced rigid-flex printed circuit board (PCB) to implement a folding robot chassis using robust, spaceflight-tolerant materials, and integrates the robot electronics directly into the chassis for added compactness. The new approach also decouples the mechanical and electrical functions of the chassis flexures for improved kinematics and lifetime. This manufacturing paradigm was used to build PUFFER (Pop-Up Flat Folding Explorer Robot), a self-actuated pop-up rover being developed to provide a low-payload-cost mobility enhancement for future NASA missions.

We present the design, modeling, and implementation of a novel pneumatic actuator, the Pneumatic Reel Actuator (PRA). The PRA is highly extensible, lightweight, capable of operating in compression and tension, compliant, and inexpensive. An initial prototype of the PRA can reach extension ratios greater than 16:1, has a force-to-weight ratio over 28:1, reach speeds of 0.87 meters per second, and can be constructed with parts totaling less than $4 USD. We have developed a model describing the actuator and have conducted experiments characterizing the actuator's performance in regards to force, extension, pressure, and speed. We have implemented two parallel robotic applications in the form of a three degree of freedom robot arm and a tetrahedral robot.

These plenaries discuss the following: Modeling the possibilities: From the Chalkboard to the Race Track to the World Beyond; Nobel Turing Challenge: Grand Challenge of AI, Robotics, and Systems Biology; Framing the International Discussion on the Weaponization of Increasingly Autonomous Technologies; EndoMaster: A Surgical Robot's Journey from the Research Lab to the Operating Theatre; Capturing Vivid 3D Models of the World from Video;Industry 4.0 - Automation and Robotics; Research at the Intersection Between Robots and Play: Designing Robots for Children's Healthcare; An Operational Platform of Cloud Robotics;and Model-based Optimization for Humanoid and Wearable Robots.

Most demonstrated mobile microrobot tasks so far have been achieved via pick-and-placing and dynamic trapping with teleoperation or simple path following algorithms. In our previous work, an untethered magnetic microgripper has been developed which has advanced functions, such as gripping objects. Both teleoperated manipulation in 2D and 3D have been demonstrated. However, it is challenging to control the magnetic microgripper to carry out manipulation tasks, because the grasping of objects so far in the literature relies heavily on teleoperation, which takes several minutes with even a skilled human expert. Here, we propose a new spin-walking locomotion and an automated 2D grasping motion planner for the microgripper, which enables time-efficient automatic grasping of microobjects that has not been achieved yet for untethered microrobots. In its locomotion, the microgripper repeatedly rotates about two principal axes to regulate its pose and move precisely on a surface. The motion planner could plan different motion primitives for grasping and compensate the uncertainties in the motion by learning the uncertainties and planning accordingly. We experimentally demonstrated that, using the proposed method, the microgripper could align to the target pose with error less than 0.1 body length and grip the objects within 40 seconds. Our method could significantly improve the time efficiency of micro-scale manipulation and have potential applications in microassembly and biomedical engineering.

This paper proposes a motion-planning method for a wrapping-with-fabric task. To wrap, robots require not only offhand paths (which represent the movement of a grasping point on fabric) but also actual robot motion. When a robot handles fabric, it must consider the range of motion and collisions. To overcome such limitations, the robot must pass fabric inter- and intra-hand. The proposition is based on the reliability of its movements. The method may be used to plan a combination of inter- and intra-hand passing motions to generate the basic movements for wrapping along an offhand path. Experiments show how, by using the proposed planning method, a dual-arm robot can wrap an L-shaped pipe.