IROS 2020 论文列表

Choosing a kinematic model for a continuum robot typically involves making a tradeoff between accuracy and computational complexity. One common modeling approach is to use the Cosserat rod equations, which have been shown to be accurate for many types of continuum robots. This approach, however, still presents significant computational cost, particularly when many Cosserat rods are coupled via kinematic constraints. In this work, we propose a numerical method that combines orthogonal collocation on the local rod curvature and forward integration of the Cosserat rod kinematic equations via the Magnus expansion, allowing the equilibrium shape to be written as a product of matrix exponentials. We provide a bound on the maximum step size to guarantee convergence of the Magnus expansion for the case of Cosserat rods, compare in simulation against other approaches, and demonstrate the tradeoffs between speed and accuracy for the fourth and sixth order Magnus expansions as well as for different numbers of collocation points. Our results show that the proposed method can find accurate solutions to the Cosserat rod equations and can potentially be competitive in computation speed.

In this paper, we propose SolarSLAM, a batteryfree loop closure method for indoor localisation. Inertial Measurement Unit (IMU) based indoor localisation method has been widely used due to its ubiquity in mobile devices, such as mobile phones, smartwatches and wearable bands. However, it suffers from the unavoidable long term drift. To mitigate the localisation error, many loop closure solutions have been proposed using sophisticated sensors, such as cameras, laser, etc. Despite achieving high-precision localisation performance, these sensors consume a huge amount of energy. Different from those solutions, the proposed SolarSLAM takes advantage of an energy harvesting solar cell as a sensor and achieves effective battery-free loop closure method. The proposed method suggests the key-point dynamic time warping for detecting loops and uses robust simultaneous localisation and mapping (SLAM) as the optimiser to remove falsely recognised loop closures. Extensive evaluations in the real environments have been conducted to demonstrate the advantageous photocurrent characteristics for indoor localisation and good localisation accuracy of the proposed method.

In recent years, there has been a growing interest in multiple robots performing a single task through different types of collaboration. There are two software challenges when deploying collaborative robots: how to specify a cooperative mission and how to program each robot to accomplish its mission. In this paper, we propose a novel software development framework to support distributed robot systems, swarm robots, and their hybrid. We extend the service-oriented and model-based (SeMo) framework [1] to improve the robustness, scalability, and flexibility of robot collaboration. To enable a casual user to specify various types of cooperative missions easily, the high-level mission scripting language is extended with new features such as team hierarchy, group service, one-to-many communication. The script program is refined to the robot codes through two intermediate steps, strategy description and task graph generation, in the proposed framework. The viability of the proposed framework is evidenced by two preliminary experiments using real robots and a robot simulator.

Manipulation in cluttered environments like homes requires stable grasps, precise placement and robustness against external contact. Towards addressing these challenges, we present the Soft-bubble gripper system that combines highly compliant gripping surfaces with dense-geometry visuotactile sensing and facilitates multiple kinds of tactile perception. We first present several mechanical design advances on the Soft-bubble sensors including a fabrication technique to deposit custom patterns to the internal surface of the sensor membrane that enables tracking of shear-induced displacement of the grasped object. The depth maps output by the internal imaging sensor are used in an in-hand proximity pose estimation framework - the method better captures distances to corners or edges on the object geometry. We also extend our previous work on tactile classification and integrate the system within a robust manipulation pipeline for cluttered home environments. The capabilities of the proposed system are demonstrated through robust execution of multiple real-world manipulation tasks.

Reinforcement Learning (RL) methods have demonstrated promising results for the automation of subtasks in surgical robotic systems. Since many trial and error attempts are required to learn the optimal control policy, RL agent training can be performed in simulation and the learned behavior can be then deployed in real environments. In this work, we introduce an open-source simulation environment providing support for position based dynamics soft bodies simulation and state-of-the-art RL methods. We demonstrate the capabilities of the proposed framework by training an RL agent based on Proximal Policy Optimization in fat tissue manipulation for tumor exposure during a nephrectomy procedure. Leveraging on a preliminary optimization of the simulation parameters, we show that our agent is able to learn the task on a virtual replica of the anatomical environment. The learned behavior is robust to changes in the initial end-effector position. Furthermore, we show that the learned policy can be directly deployed on the da Vinci Research Kit, which is able to execute the trajectories generated by the RL agent. The proposed simulation environment represents an essential component for the development of next-generation robotic systems, where the interaction with the deformable anatomical environment is involved.

In this paper we present the design, fabrication, testing, and control of a 0.4 g milliscale robot employing a soft polymer flexure transmission for rapid ground movement. The robot was constructed through a combination of two methods: smart-composite-manufacturing (SCM) process to fabricate the actuators and robot chassis, and silicone elastomer molding and casting to fabricate a soft flexure transmission. We actuate the flexure transmission using two customized piezoelectric (PZT) actuators that attach to the transmission inputs. Through high-frequency oscillations, the actuators are capable of exciting vibrational resonance modes of the transmission which result in motion amplification on the transmission output. Directional spines on the transmission output generate traction force with the ground and drive the robot forward. By varying the excitation frequency of the soft transmission we can control locomotion speed, and when the transmission is oscillated at its resonance frequency we achieve high speeds with a peak speed of 439 mm/s (22 body lengths/s). By exciting traveling waves through the soft transmission, we were able to control the steering direction. Overall this paper demonstrates the feasibility of generating resonance behavior in millimeter scale soft robotic structures to achieve high-speed controllable locomotion.

More than ever, people spend the workday seated in front of a computer, which contributes to health issues caused by excess sedentary behavior. While breaking up long periods of sitting can alleviate these issues, no scalable interventions have had long-term success in motivating activity breaks at work. We believe that socially assistive robotics (SAR), which combines the scalability of e-health interventions with the motivational social ability of a companion or coach, may offer a solution for changing sedentary habits. To begin this work, we designed a SAR system and conducted a within-subjects study with N = 19 participants to compare their experiences taking breaks using the SAR system versus an alarm-like device for one day each in participants' normal workplaces. Results indicate that both systems had similar effects on sedentary behavior, but the SAR system led to greater feelings of pleasure, enjoyment, and engagement. Interviews yielded design recommendations for future systems. We find that SAR systems hold promise for further investigations of aiding healthy habit formation in work settings.

In this paper, we present the second version of a reconfigurable modular legged robot, Snapbot V2. The mechanical design of Snapbot V2 is enhanced for better dynamic performance and robust connection with modular legs. A motion generator for locomotion is developed to achieve various locomotion skills in one to six-leg configurations. The locomotion is tested on a multi-body dynamic simulation model and implemented on a physical robot as well. A visual detection is implemented with a camera module to recognize the robot’s configuration. By detecting the particular color of the parts at the leg module, the robot can recognize the number and location of the connected legs. Based on the recognized configuration, Snapbot V2 selects the proper locomotion style automatically.

The presence of any type of defect on the glass screen of smart devices has a great impact on their quality. We present a robust semi-supervised learning framework for intelligent micro-scaled localization and classification of defects on a 16K pixel image of smartphone glass. Our model features the efficient recognition and labeling of three types of defects: scratches, light leakage due to cracks, and pits. Our method also differentiates between the defects and light reflections due to dust particles and sensor regions, which are classified as non-defect areas. We use a partially labeled dataset to achieve high robustness and excellent classification of defect and non-defect areas as compared to principal components analysis (PCA), multi-resolution and information-fusion-based algorithms. In addition, we incorporated two classifiers at different stages of our inspection framework for labeling and refining the unlabeled defects. We successfully enhanced the inspection depth-limit up to 5 microns. The experimental results show that our method outperforms manual inspection in testing the quality of glass screen samples by identifying defects on samples that have been marked as good by human inspection.

Under the circumstances that social robots are increasingly being developed and studied in service encounters at public spaces, are they introduced into residential environments (i.e., private space)? This study hypothesizes that a personal assistant device in residential environments should wear human-like appearance to engage in service as conversation partner. We implemented the interaction design that provides regular services as the current personal assistant and additional service as conversation partner, and then conducted a field experiment where the participants stayed in the hotel rooms with a smart speaker or a social robot. The results support the hypothesis in that of conversation amount and emotional experience by conversation. The results also suggest the possibility of commercial service, namely conversational advertisement through social robots.

Quadrupedal locomotion skills are challenging to develop. In recent years, deep Reinforcement Learning promises to automate the development of locomotion controllers and map sensory observations to low-level actions. Moreover, the full robot dynamics model can be exploited, but no model-based simplifications are to be made. In this work, a method for developing controllers for the Laelaps II robot is presented and applied to motions on slopes up to 15°. Combining deep reinforcement learning with trajectory planning at the toe level, reduces complexity and training time. The proposed control scheme is extensively tested in a Gazebo environment similar to the treadmill-robot environment at the Control Systems Lab of NTUA. The learned policies produced promising results.

This paper introduces a constraint-based skill framework for programming robot applications. Existing skill frameworks allow application developers to reuse skills and compose them sequentially or in parallel. However, they typically assume that the skills are running independently and in a nominal condition. This limitation hinders their applications for more involved and realistic scenarios e.g. when the skills need to run synchronously and in the presence of disturbances. This paper addresses this problem in two steps. First, we revisit how constraint-based skills are modeled. We classify different skill types based on how their progress can be evaluated over time. Our skill model separates the constraints that impose task-consistency and the constraints that make the skills progress i.e. reaching their end conditions. Second, this paper introduces composition patterns that couple skills in parallel such that they are executed in a synchronized manner and reactive to disturbances. The effectiveness of our framework is evaluated on a dual-arm robotics setup that performs an industrial assembly task in the presence of disturbance.

We present a novel end-to-end single-shot method that segments countable object instances (things) as well as background regions (stuff) into a non-overlapping panoptic segmentation at almost video frame rate. Current state-of-the-art methods are far from reaching video frame rate and mostly rely on merging instance segmentation with semantic background segmentation, making them impractical to use in many applications such as robotics. Our approach relaxes this requirement by using an object detector but is still able to re-solve inter- and intra-class overlaps to achieve a non-overlapping segmentation. On top of a shared encoder-decoder backbone, we utilize multiple branches for semantic segmentation, object detection, and instance center prediction. Finally, our panoptic head combines all outputs into a panoptic segmentation and can even handle conflicting predictions between branches as well as certain false predictions. Our network achieves 32.6% PQ on MS-COCO at 23.5 FPS, opening up panoptic segmentation to a broader field of applications.

Super-coiled polymer (SCP) artificial muscles have many interesting properties that show potentials for making high performance bionic devices. To realize human-like robotic devices from this type of actuator, it is important for the SCP driven mechanisms to achieve human-like performance, such as compliant behaviors through antagonistic mechanisms. This paper presents the simultaneous position-stiffness control of an antagonistic joint driven by hybrid twisted-coiled polymer actuation bundles made from Spandex and nylon fibers, which is a common human compliant behavior. Based on a linear model of the system, which is identified and verified experimentally, a controller based on model predictive control (MPC) is designed. The MPC performance is enhanced by the incorporation of time delay estimation to estimate model variations and external disturbances. The controlled system is verified through simulations and experiments. The results show the controller's ability to control the joint angle with the highest position error of 0.6 degrees while changing joint stiffness, verified with step command and sinusoidal reference with composite frequencies of 0.01Hz to 0.1Hz.

Force modulation of robotic manipulators has been extensively studied for several decades but is not yet commonly used in safety-critical applications due to a lack of accurate interaction contact modeling and weak performance guarantees - a large proportion of them concerning the modulation of interaction forces. This study presents a high-level framework for simultaneous trajectory optimization and force control of the interaction between manipulator and soft environments. Sliding friction and normal contact force are taken into account. The dynamics of the soft contact model and the manipulator dynamics are simultaneously incorporated in a trajectory optimizer to generate desired motion and force profiles. A constrained optimization framework based on Differential Dynamic Programming and Alternative Direction Method of Multipliers has been employed to generate optimal control inputs and high-dimensional state trajectories. Experimental validation of the model performance is conducted on a soft substrate with known material properties using a Cartesian space force control mode. Results show a comparison of ground truth and predicted model based contact force states for multiple Cartesian motions and the validity range of the friction model. The proposed high-level planning has the potential to be leveraged for medical tasks involving manipulation of compliant, delicate, and deformable tissues.

Container loading by a picking robot is an important challenge in the logistics industry. When designing such a robotic system, item picking and placing have been planned individually thus far. However, since the condition of picking an item affects the possible candidates for placing, it is preferable to plan picking and placing simultaneously. In this paper, we propose a deep reinforcement learning (DRL) method for simultaneously planning item picking and placing. A technical challenge in the simultaneous planning is its scalability: even for a practical container size, DRL can be computationally intractable due to large action spaces. To overcome the intractability, we adopt a fully convolutional network for policy approximation and determine the action based only on local information. This enables us to produce a shared policy which can be applied to larger action spaces than the one used for training. We experimentally demonstrate that our method can successfully solve the simultaneous planning problem and achieve a higher occupancy rate than conventional methods.

Automobiles or robots with advanced autonomous systems are equipped with multiple types of sensors to overcome different weather and geographical conditions. These sensors generally have various data delays and sampling rates. Additionally, the communication delays or time synchronization errors between the onboard computers significantly affect the robustness and accuracy of localization for autonomous vehicles. In this paper, the simultaneous estimation of vehicle position and sensor delays using a Gaussian process based moving horizon estimation (GP-MHE) is presented. The GP-MHE can estimate the unknown delays of multiple sensors with the resolution less than that of GP-MHE sampling rate. The localization performance of GP-MHE was confirmed using full-vehicle simulator, then evaluated in a real vehicle experiment on a highway scenario. Experimental result verified the sufficient localization accuracy of sub 0.3m using data that had irregular sampling rate and delay of more than 150ms. The proposed algorithm extends the capability of integrating various data with large unknown delays for vehicles, robots, drones and remote autonomy.

Ionic polymer-metal composites (IPMC) actuators are popular because they can be driven at a low voltage, possess excellent responsiveness, and can perform soft motions similar to that of living creatures. Conventional IPMC soft robots are manufactured by cutting and assembling IPMC sheets. However, using this conventional process to stably manufacture three-dimensional (3D)-shaped soft robots is difficult. To mitigate this problem, we propose a new method for fabricating 3D IPMC actuators in which several surface electrodes are separately fabricated from a single ion-exchange membrane. We refer to our proposal as the simultaneous 3D forming and patterning (SFP) method. Unlike the conventional IPMC fabrication process, the SFP method requires only one step to fix the ion-exchange membrane to contact masks. First, we briefly describe IPMC actuators, before introducing the proposed SFP method in detail. Next, we describe our investigations of the patterning resolution for the surface electrode using the proposed method. We fabricated two soft robot prototypes using the proposed method. The first robot is a starfish-type soft robot. Its surface electrode can be patterned in a plane using the proposed method, and independent driving is possible by applying voltage individually to the divided electrodes. The second prototype is a sea anemone-type soft robot, wherein surface electrodes can be patterned on a 3D curved surface to form a 3D shape.

We present a simple, fast, and light-weight RNN based framework for forecasting future locations of humans in first person monocular videos. The primary motivation for this work was to design a network which could accurately predict future trajectories at a very high rate on a CPU. Typical applications of such a system would be a social robot or a visual assistance system "for all", as both cannot afford to have high compute power to avoid getting heavier, less power efficient, and costlier. In contrast to many previous methods which rely on multiple type of cues such as camera ego-motion or 2D pose of the human, we show that a carefully designed network model which relies solely on bounding boxes can not only perform better but also predicts trajectories at a very high rate while being quite low in size of approximately 17 MB. Specifically, we demonstrate that having an auto-encoder in the encoding phase of the past information and a regularizing layer in the end boosts the accuracy of predictions with negligible overhead. We experiment with three first person video datasets: CityWalks, FPL and JAAD. Our simple method trained on CityWalks surpasses the prediction accuracy of state-of-the-art method (STED) while being 9.6x faster on a CPU (STED runs on a GPU). We also demonstrate that our model can transfer zero-shot or after just 15% fine-tuning to other similar datasets and perform on par with the state-of-the-art methods on such datasets (FPL and DTP). To the best of our knowledge, we are the first to accurately forecast trajectories at a very high prediction rate of 78 trajectories per second on CPU.