IROS 2015 论文列表

In current flexible endoscopy, manipulating the endoscope is a major problem for surgeons. No surgeon can master the procedure without much experience. Accordingly, the objective of this study is to refine our Robotic Flexible Laparoscope System (RFLS) with more useful functions. We design a new kind of laparoscope mechanism suited for our RFLS. Furthermore, in maneuvering the laparoscope intuitively, the most significant advantage is the ability of RFLS can at least save three anatomical positions, which could be retrieved by a single command with small errors. Moreover, protective algorithm is also included in our system to make sure that over rotation of the gyro sensor, which is mounted the head, does not cause any damage. Experimental results demonstrate that the articulated flexible laparoscope can always memorize the required points and return back to those points in all necessary orientations.

This work presents a human-robot cooperative approach for infrastructure inspection. The goal is to create a robot that assists the human inspector during hammer sounding inspections. Hammer sounding is a frequently used inspection technique that detects invisible defects under the surface of concrete by striking the surface with a hammer and listening the resulting sound. The conventional hammer sounding inspection is time-consuming, and there is no convenient way to represent exhaustively the test results. The proposed approach solves these two problems by having an assistant robot following the inspector, and always being able to look at the hammer impact position. The assistant robot accurately estimates the position of the impact in real-time and creates a detailed representation of the test results. Experimental results show the process for creating the detailed inspection report. The accuracy of the human-robot cooperative approach is evaluated for a real world application. The average error of the impact point estimation was 32 millimeters and the standard deviation was 30 millimeters.

This paper describes a Robot-Audition based Car Human Machine Interface (RA-CHMI). A RA-CHMI, like a car navigation system, has difficulty dealing with voice commands, since there are many noise sources in a car, including road noise, air-conditioner, music, and passengers. Microphone array processing developed in robot audition, may overcome this problem. Robot audition techniques, including sound source localization, Voice Activity Detection (VAD), sound source separation, and barge-in-able processing, were introduced by considering the characteristics of RA-CHMI. Automatic Speech Recognition (ASR), based on a Deep Neural Network (DNN), improved recognition performance and robustness in a noisy environment. In addition, as an integrated framework, HARK-Dialog was developed to build a multi-party and multi-modal dialog system, enabling the seamless use of cloud and local services with pluggable modular architecture. The constructed multi-party and multimodal RA-CHMI system did not require a push-to-talk button, nor did it require reducing the audio volume or air-conditioner when issuing speech commands. It could also control a four-DOF robot agent to make the system's responses more understandable. The proposed RA-CHMI was validated by evaluating essential techniques in the system, such as VAD and DNN-ASR, using real speech data recorded during driving. The entire design of the RA-CHMI system, including the system response time and the proper use of cloud/local services, are also discussed.

This paper presents a novel approach for robot instruction for assembly tasks. We consider that robot programming can be made more efficient, precise and intuitive if we leverage the advantages of complementary approaches such as learning from demonstration, learning from feedback and knowledge transfer. Starting from low-level demonstrations of assembly tasks, the system is able to extract a high-level relational plan of the task. A graphical user interface (GUI) allows then the user to iteratively correct the acquired knowledge by refining high-level plans, and low-level geometrical knowledge of the task. This combination leads to a faster programming phase, more precise than just demonstrations, and more intuitive than just through a GUI. A final process allows to reuse high-level task knowledge for similar tasks in a transfer learning fashion. Finally we present a user study illustrating the advantages of this approach.

This paper presents the implementation and evaluation results of the German research project SERROGA (2012 till mid 2015), which aimed at developing a robot companion for domestic health assistance for older people that helps keeping them physically and mentally fit to remain living independently in their own homes for as long as possible. The paper gives an overview of the developed companion robot, its system architecture, and essential skills, behaviors, and services required for a robotic health assistant. Moreover, it presents a new approach allowing a quantitative description and assessment of the navigation complexity of apartments to make them objectively comparable for function tests under real-life conditions. Based on this approach, the results of function tests executed in 12 apartments of project staff and seniors are described. Furthermore, the paper presents findings of a case study conducted with nine seniors (aged 68-92) in their own homes, investigating both instrumental and social-emotional functions of a robotic health assistant. The robot accompanied the seniors in their homes for up to three days assisting with tasks of their daily schedule and health care, without any supervising person being present on-site. Results revealed that the seniors appreciated the robot's health-related instrumental functions and even built emotional bonds with it.

To analyze auditory scenes of robots' surrounding environments, not only speeches but also non-speech sounds are important, which are spatially distributed and have different spectral and temporal characteristics. Thus, this paper investigates Acoustic Event Identification (AEI) which includes problems of localization, detection, and identification of sound sources. To achieve AEI by a robot in a real environment, we first propose to use a robot audition framework including sound source localization and separation to localize, detect, and separate acoustic events. For the identification, we propose two Bayesian models, iterative Latent Dirichlet Allocation (it-LDA) and Nested Pitman-Yor process with Uncertainty Compensation (NPY-UC). it-LDA and NPY-UC extract noise-robust sound-units and sound-words, respectively, and they consider probabilistic spectral and temporal uncertainties to robustify AEI against harsh environments such as noise and reverberation, etc. We have implemented these proposed methods using a robot-embedded microphone array. The preliminary results showed 5–18 pts improvement compared to a conventional GMM method in noisy environments thanks to the Bayesian framework in consideration of uncertainties.

Robots performing general purpose plans must deal with a wide variety of contexts. Situations they encounter might differ only in subtle, but important details in context and parameterization that have a massive impact on an action's outcome. To avoid the effort of encoding all possible combinations of subtleties into plans, we present a prediction framework that gives robot agents an intuition of their actions' effects and for choosing parameter values that have proven to be useful before. We let a robot form these predictions and expectations from episodic memories collected during earlier plan executions, improving its own behavior with every new situation encountered. We evaluate and explain our approach using experiments performed on a PR2 robot performing complex mobile manipulation activities in a kitchen environment.

Since its official introduction in 2012, the Robot Web Tools project has grown tremendously as an open-source community, enabling new levels of interoperability and portability across heterogeneous robot systems, devices, and front-end user interfaces. At the heart of Robot Web Tools is the rosbridge protocol as a general means for messaging ROS topics in a client-server paradigm suitable for wide area networks, and human-robot interaction at a global scale through modern web browsers. Building from rosbridge, this paper describes our efforts with Robot Web Tools to advance: 1) human-robot interaction through usable client and visualization libraries for more efficient development of front-end human-robot interfaces, and 2) cloud robotics through more efficient methods of transporting high-bandwidth topics (e.g., kinematic transforms, image streams, and point clouds). We further discuss the significant impact of Robot Web Tools through a diverse set of use cases that showcase the importance of a generic messaging protocol and front-end development systems for human-robot interaction.

Satellite positioning is a key technology for autonomous navigation in outdoors environments. When using standalone computation with mono-frequency receivers, positioning errors are not in accordance with the required performance. Nevertheless, since errors are strongly time-correlated, a GPS fix is quite informative if a shaping model of the positioning errors is carefully handled and made possible by exteroceptive sensors. When driving in a road with a camera detecting lane markings, the lateral error is directly observable by using a lane marking map. It can be well modeled by mixing auto-regressive and random constant models. An algebraic observability study is conducted to prove that this modeling is completely observable in a road frame. A new road invariant Extended Kalman Filter (EKF) is then presented to conserve the observability of every component of the state vector for any road whatever its orientation. The filter manages road changes by using bijective transformations that are detailed. Real experimental results indicate that the performance of the estimation process is significantly improved compared to a classic EKF that is implemented in a fixed working frame with a less informative error modeling.

This paper reports on a Gaussian belief-space planning formulation for mobile robots that includes random measurement acquisition variables that model whether or not each measurement is actually acquired. We show that maintaining the stochasticity of these variables in the planning formulation leads to a random belief covariance matrix, allowing us to consider the risk associated with the acquisition in the objective function. Inspired by modern portfolio theory and utility optimization, we design objective functions that are risk-averse, and show that risk-averse planning leads to decisions made by the robot that are desirable when operating under uncertainty. We show the benefit of this approach using simulations of a planar robot traversing an uncertain environment and of an underwater robot searching for loop-closure actions while performing visual SLAM.

We present a novel approach of active object categorization based on an iterative Bayesian method using capacitive sensing during object manipulation. The approach uses a novel type of capacitive sensor, which can measure internal properties of materials that are inaccessible to vision or tactile sensing. The electrodes of this capacitive sensor are sufficiently flexible and thin to be attached to various types of robot tools, including humanoid fingers and palms. They are mechanically robust and wear resistant. In comparison to earlier capacitive sensors systems, we perform single ended and differential measurements over an array of electrodes, and coordinate measurement with robot manipulation to extract information not available from static measurements. We demonstrate the capability of our active object categorization system in the James robot bartender system. This system can manipulate objects and measure continuously in order to categorize empty and non-empty bottles. The principle of capacitive sensing during manipulation can be applied to more general object manipulation tasks in robotics and also in other fields of industrial automation.

This paper presents an active release method of microobject for the improvement of the position accuracy after releasing by using 3D high speed motions of an end effector. In the micro manipulation, the release task is the challenge work due to adhesion forces. To overcome the adhesion force and to place microobject accurately on the desired location, in this paper, we propose a high speed motion by analyzing dynamic model of manipulated end effector and attached microbeads. Two fingered microhand driven by DC motors and PZT actuators is utilized for this paper. Parallel mecahnism with three PZT actuators was used for making 3D motion at high speed. To generatge high acceleration of end effector, many researchers applied simple vibration by using an additional PZT actuator. In our research, 3D high speed motion with large amplitude was achieved by only using a compacted parallel mechanism. To verify the advantage of the proposed motion, we compare five motions, 1D motions (X, Y, and Z direction) and circular motions (clockwise and counterclockwise direction), by changing the frequency and moving distance of the end effector. From these results of experiments, we conclude that the circular motion can detach microobjects with high placing accuracy after release.

Reinforcement learning of motor skills is an important challenge in order to endow robots with the ability to learn a wide range of skills and solve complex tasks. However, comparing reinforcement learning against human programming is not straightforward. In this paper, we create a motor learning framework consisting of state-of-the-art components in motor skill learning and compare it to a manually designed program on the task of robot tetherball. We use dynamical motor primitives for representing the robot's trajectories and relative entropy policy search to train the motor framework and improve its behavior by trial and error. These algorithmic components allow for high-quality skill learning while the experimental setup enables an accurate evaluation of our framework as robot players can compete against each other. In the complex game of robot tetherball, we show that our learning approach outperforms and wins a match against a high quality hand-crafted system.

In this paper, a variable admittance controller based on reinforcement learning is proposed for human-robot co-manipulation tasks. Setting as the goal of the reinforcement learning algorithm the minimisation of the jerk throughout a point-to-point movement, the proposed controller can learn the appropriate damping for effective cooperation without any prior knowledge of the target position or other task characteristics. The performance of the proposed variable admittance controller is investigated on a co-manipulation task with a number of subjects using a KUKA LWR robot, demonstrating considerable reduction both in the effort required by the operator and in the completion time of the task.

The presence of robots not only in industrial settings but also in operating rooms is increasing with advancements in technology. They are not only huge machines carrying out tedious and arduous tasks while being caged behind fences, but also work in collaboration, close proximity of, and in cooperation with humans. Image guided minimally invasive approaches to accurately navigate a robot to precise anatomical locations can be followed only once the robot is registered to the medical imaging system. In this paper, we present an approach to register a robotic system to a medical imaging system without the use of any tracking device or continuous X-ray imaging. The system consists of a lightweight robot equipped with internal torque sensors. The registration is realized by a series of landmark transformations. The robot is manually moved and guided to distinct landmarks whose positions are known in the coordinate system of the imaging system. By driving the robot to these distinct landmarks, their position relative to the coordinate system of the robotic system is also known. By comparing the respective positions of the landmarks in the two coordinate systems, both systems are registered. With 8 screws on the operating table used as landmarks for this registration, we obtain a median error of [6.9, 20.6, 18.6] mm and a standard deviation of [2.9, 2.6, 2.2] mm when compared to an X-ray based ground truth.

Modern approaches to monocular SLAM retain all observations and repeatedly perform bundle adjustment in order to overcome the inconsistency problem that arises in approaches that marginalise out camera positions. Bundle adjustment is inherently an expensive operation and so sparse matrix techniques and double window optimisation on sparsely sampled key-frames are employed to minimize the computational cost.

The use of emotional states for Human-Robot Interaction (HRI) has attracted considerable attention in recent years. One of the most challenging tasks is to recognize the spontaneous expression of emotions, especially in an HRI scenario. Every person has a different way to express emotions, and this is aggravated by the complexity of interaction with different subjects, multimodal information and different environments. We propose a deep neural model which is able to deal with these characteristics and which is applied in recognition of complex mental states. Our system is able to learn and extract deep spatial and temporal features and to use them to classify emotions in sequences. To evaluate the system, the CAM3D corpus is used. This corpus is composed of videos recorded from different subjects and in different indoor environments. Each video contains the recording of the upper-body part of the subject expressing one of twelve complex mental states. Our system is able to recognize spontaneous complex mental states from different subjects and can be used in such an HRI scenario.

In this paper we present a collision avoidance system based on visual detection. Our hardware consists of a Hummingbird quadrotor equipped with a large red marker with two built-in fish-eye cameras. Fusion of the measurements from the two cameras is done using a Gaussian-mixture probability hypothesis density filter, which allows for tracking several aircrafts at the same time. Our collision avoidance algorithm is based on navigation functions designed to cope with cameras characterized by limited field of view. Its mathematical correctness has been proven in a former paper [1]. The collision avoidance maneuver is performed without the vehicles explicitly exchanging information via communication but instead relying solely on on-board sensors. Our system has been validated in an indoor space with four different collision scenarios. Trajectory data was recorded with an external motion capture system and demonstrate good robustness against sensing noise.

We present a vision cognition framework for tomato harvesting humanoid robot based on geometrical and physical reasoning. Inspired from the natural human harvesting behaviour, our goal is to build a humanoid robot to pick tomatoes autonomously or with minimal human efforts. The proposed vision approach uses fusion of calibrated observation data from two RGB-D sensors installed on the head and the hand of the humanoid. We observe the natural human harvesting behaviour and equip our robot with similar grippers to follow the same picking processes for a specific fruit. In the vision approach, we mainly focus on modelling fruits in one branch and then estimating the pedicel direction of each fruit in a branch. Through pointcloud model segmentation, the primitive shape model of each fruit can be obtained and we consider a simple fact that crops in one branch should remain stable with respect to gravity and interaction forces from neighbouring crops in the branch. According to this assumption, a probabilistic model is created and the picking order in the branch is assigned under the evaluated geometrical structure. In the experiments, we tested harvesting of real tomatoes on actual branches and evaluated the successful harvesting rate.