IROS 2016 Papers

In this paper, we propose a novel assistance strategy for stair ascent walking using our robotic hip exoskeleton. Our strategy exploits foot contact event estimated by an inertial measurement unit (IMU) and can detect user intention as well as reflect user preference. In our strategy, a gait cycle is divided into 4 phases and the transitions between the phases are based on events that are unavoidable and can be detected reliably using the sensors available for our exoskeleton. The proposed strategy presents criteria for the initiation and termination of assistance by recognizing user intention, as well as methods to adjust the timing and the amount of assistance corresponding to user preference. When each step starts, the duration of assistance is determined and the torque profile for the whole step is planned ahead. We demonstrate the validity of the proposed strategy for stair ascent and examine its effects on hip joint angle trajectory through experimental results.

AprilTags and other passive fiducial markers require specialized algorithms to detect markers among other features in a natural scene. The vision processing steps generally dominate the computation time of a tag detection pipeline, so even small improvements in marker detection can translate to a faster tag detection system. We incorporated lessons learned from implementing and supporting the AprilTag system into this improved system. This work describes AprilTag 2, a completely redesigned tag detector that improves robustness and efficiency compared to the original AprilTag system. The tag coding scheme is unchanged, retaining the same robustness to false positives inherent to the coding system. The new detector improves performance with higher detection rates, fewer false positives, and lower computational time. Improved performance on small images allows the use of decimated input images, resulting in dramatic gains in detection speed.

While the topic of security in industrial applications has gained some momentum in recent years, there are still severe security vulnerabilities which are actively exploited for attacks. The robot operating system (ROS) is expected to further grow in usage and to be used in many industrial applications. Analysis, however, shows that it lacks several security enhancements in order to make it suitable for industrial use. In its current state, false data and commands can be injected posing a possible safety risk for the resulting product and humans in the production. In addition, data may be eavesdropped and used by outsiders to gain insight into the production process. In this paper we propose a security architecture intended for use on top of ROS on the application level. We use a dedicated authorization server to ensure that only valid nodes are part of the application. Cryptographic methods ensure data confidentiality and integrity. We show in a demonstration with a collaborative robot how our architecture can be used to secure a ROS-based application.

In this paper, we present an online landmark selection method for distributed long-term visual localization systems in bandwidth-constrained environments. Sharing a common map for online localization provides a fleet of autonomous vehicles with the possibility to maintain and access a consistent map source, and therefore reduce redundancy while increasing efficiency. However, connectivity over a mobile network imposes strict bandwidth constraints and thus the need to minimize the amount of exchanged data. The wide range of varying appearance conditions encountered during long-term visual localization offers the potential to reduce data usage by extracting only those visual cues which are relevant at the given time. Motivated by this, we propose an unsupervised method of adaptively selecting landmarks according to how likely these landmarks are to be observable under the prevailing appearance condition. The ranking function this selection is based upon exploits landmark co-observability statistics collected in past traversals through the mapped area. Evaluation is performed over different outdoor environments, large time-scales and varying appearance conditions, including the extreme transition from day-time to night-time, demonstrating that with our appearance-dependent selection method, we can significantly reduce the amount of landmarks used for localization while maintaining or even improving the localization performance.

We present an efficient anytime motion planner for mobile robots that considers both other dynamic obstacles and uncertainty caused by various sensors and low-level controllers. Our planning algorithm, which is an anytime extension of the Rapidly-exploring Random Belief Tree (RRBT), maintains the best possible path throughout the robot execution, and the generated path gets closer to the optimal one as more computation resources are allocated. We propose a branch-and-bound method to cull out unpromising areas by considering path lengths and uncertainty. We also propose an uncertainty-aware velocity obstacle as a simple local analysis to avoid dynamic obstacles efficiently by finding a collision-free velocity. We have tested our method with three benchmarks that have non-linear measurement regions or potential collisions with dynamic obstacles. By using the proposed methods, we achieve up to five times faster performance given a fixed path cost.

An extension based on attention and anticipation of a robot vision pipeline for object recognition in RGBD images from low-cost sensors like MS Kinect or ASUS Xtion is presented. This work originated in research on an industrial application scenario, namely shipping-container unloading, but it is applicable to advanced manipulation tasks in unstructured environments in general where the perception must be very robust while being as fast as possible. For these scenarios, we build on our previous work that proved to be competitive in cluttered scenes in table-top scenarios and which forms the backbone of our RGBD object recognition. It is further enhanced by two main contributions. First, a simple but very effective form of anticipation as top-down expectations of the evolution of the scene due to the actions of the robot is used to speed up the processing. Second, attention is used as a mechanism for further speed-up by focusing processing only on certain regions of interest of the scene based also on an anticipation mechanism. The method is analyzed in experiments using real-world data from an industrial demonstration set-up.

The stabilization of man-made artificial systems has been achieved by sensor based state feedback control with high computational bandwidth and high stiffness structures. In contrast, many biological systems have been achieved similar or superior stable behavior with low speed signal transmission via nervous systems, which is easy to introduce unstable performance from a control engineering perspective. In order to explain this phenomenon, the concept of self-stabilization has recently been proposed and investigated. Self-stabilization is defined as the ability to restore its original state after a disturbance without any feedback control. In this paper, the self-stabilizing function of a musculoskeletal system for arbitrary motion in the vertical plane is analytically investigated using Lyapunov stability theory. Based on this investigation we propose a design method to realize the self-stabilizing function of a musculoskeletal system, and experimentally verify that the self-stabilizing function can be physically realized by the proposed Lyapunov function.

The sit-to-stand movement is an apparently simple yet fundamental activity of daily life. Failure of performing this movement strongly impacts the quality of life of an increasing number of elderly people. Much research thus focuses on assisting this motion. The time necessary for rising up from a sit position is very short for healthy subjects, in the order of few seconds. Using similar speeds for the assisted motion would create safety concerns, hence slower speeds are usually employed. In this paper we experimentally investigate the effects of this speed reduction. We detail the relationship among robot's speed, forces acting on the robot's user and muscular activation. From the results of this analysis we derive indications on the speeds appropriate for assisting the sit-to-stand movement.

We consider an online planning algorithm for partially observable Markov decision processes (POMDPs), called Anytime Error Minimization Search 2 (AEMS2). Despite the considerable success it has enjoyed in robotics and other problems, no quantitative analysis exists of the relationship between its near-optimality and the computation invested. Exploiting ideas from fully-observable MDP planning, we provide here such an analysis, in which the relationship is modulated via a measure of problem complexity called near-optimality exponent. We illustrate the exponent for some interesting POMDP structures, and examine the role of the informative heuristics used by AEMS2 in the guarantees. In the second part of the paper, we introduce a domestic assistance problem in which a robot monitors partially observable switches and turns them off if needed. AEMS2 successfully solves this task in real experiments, and also works better than several state of the art planners in simulation comparisons.

In this paper we described the development of both the hardware and the algorithms for a novel laser vision system suitable for measuring distances from both solid and mesh-like targets in underwater environments. The system was developed as a part of the AQUABOT project that developed an underwater robotic system for autonomous inspection of offshore aquaculture installation. The system takes into account the hemispherical optics typical in underwater vehicle designs and implements an array of line-lasers to ensure that mesh-like targets provide reflections in a consistent manner. The developed algorithms for the laser vision system are capable of providing either raw pointcloud data sets from each laser or with additional processing high level information like distance and relative orientation of the target with respect to the ROV can be recovered. An automatic calibration procedure along with the accompanying hardware that was developed, is described in this paper, to reduce the calibration overhead required by regular maintenance operations as is typical for underwater vehicles operating in sea-water. A set of experimental results in controlled laboratory environment as well as at offshore aquaculture installations demonstrate the performance of the system.

Artificial sensory system is promising to navigate in cluttered and turbid underwater environment by achieving similar functions of biological electrosense of weakly electric fish. In this paper we designed an electrosensory membrane that can operate in a full 3-dimensional mode. Algorithms on the object localization were also designed and tested based on numerical methods of electric field forward simulation. We combined the statistic learning method by training a multi-layer neural network and a probabilistic approach by applying a constrained unscented Kalman filter (CUKF). This exploits the merits of fast estimation and precise signal marching process. Experimental results showed that the detection and localization with the reported sensor were quick and accurate, with errors of around 10 mm using one-step neural network mapping and about 5 mm in close-range using CUKF. This work demonstrated the effectiveness of proposed electrosensory membrane and algorithms.

Object representation is one of the most challenging tasks in robotics because it must provide reliable information in real-time to enable the robot to physically interact with the objects in its environment. To ensure reliability, a global object descriptor must be computed based on a unique and repeatable object reference frame. Moreover, the descriptor should contain enough information enabling to recognize the same or similar objects seen from different perspectives. This paper presents a new object descriptor named Global Orthographic Object Descriptor (GOOD) designed to be robust, descriptive and efficient to compute and use. The performance of the proposed object descriptor is compared with the main state-of-the-art descriptors. Experimental results show that the overall classification performance obtained with GOOD is comparable to the best performances obtained with the state-of-the-art descriptors. Concerning memory and computation time, GOOD clearly outperforms the other descriptors. Therefore, GOOD is especially suited for real-time applications.

This paper introduces a performance oriented method for simulating stable free-floating satellite dynamics on a position controlled robot. Intrinsic latencies found in robot controllers, i.e. between input and output data, are known to produce stability issues and performance degradation. These issues are even more apparent during contact phases, where impact dynamics play a major role. The approach presented in this paper guarantees stability through passivity and preserves the performance through the use of an optimal damping. The energy produced by delays found in the closed loop system is monitored and dissipated when necessary. In order to implement the dynamics accurately, the damping process is formulated as an optimization problem. Thus, over-dissipation can be avoided and the system becomes less conservative. Performance and effectiveness of the method are shown in simulation and verified experimentally on a position controlled seven degrees of freedom Light Weight Robot equipped with a force-torque sensor at the end-effector.

We propose an efficient path planning method for an autonomous underwater vehicle (AUV) used for the long-range and long-term ocean monitoring. We consider both the spatio-temporal variations of ocean phenomena and the disturbances caused by ocean currents, and design an approach integrating the information-theoretic and decision-theoretic planning frameworks. Specifically, the information-theoretic component employs a hierarchical structure and plans the most informative observation way-points for reducing the uncertainty of ocean phenomena modeling and prediction; whereas the decision-theoretic component plans local motions by taking into account the non-stationary ocean current disturbances. We validated the method through simulations with real ocean data.

This paper introduces a new controller for dual-user training systems, designed by way of an energy based approach. Dual-user training systems are useful for supervised hands-on training when a trainer shows the right gestures to a trainee and where the forces to apply on the tools are difficult to dose. An energy shared control (ESC) based architecture is proposed, based on an intrinsically passive authority sharing mechanism which is enhanced to provide a full force feedback to both users. As this enhancement may violate the natural passivity of the system, a passivity controller is introduced. A task based comparative study with two other dual-user schemes (Complementary Linear Combination (CLC) and Masters Correspondence with Environment Transfer (MECT) from [1] is conducted, which reveals analogous performances. Real-time experiments demonstrate good tracking performances.

Pick-and-place regrasp extends the manipulation capability of a robot by using a sequence of regrasps to accomplish tasks that are not possible using a single grasp due to constraints such as kinematics or collisions between the robot and the environment. Previous work on pick-and-place only leveraged static passive devices for intermediate placements, and thus is limited in the flexibility and robustness to reorient an object. In this paper, we extend the reorientation capability of a pick-and-place regrasp by adding an actively actuated gripper fixed in the working cell, and using it as the intermediate location for regrasping. In particular, our method automatically computes the stable placements of an object being hold in the gripper support, finds a rich set of force-closure grasps, performs k-means based grasp clustering, generates a graph of regrasp actions, and searches for the optimal regrasp sequence. To compare the regrasping performance with typical passive supports, we evaluate the success rate while performing tasks on various models. Experiments on reorientation tasks validate the benefit of using an actively actuated gripper for regrasp placement.

Motivated by the emerging needs to improve the quality of life for the elderly and disabled individuals who rely on wheelchairs for mobility, and who might have limited or no hand functionality at all, we propose an egocentric computer vision based co-robot wheelchair to enhance their mobility without hand usage. The co-robot wheelchair is built upon a typical commercial power wheelchair. The user can access 360 degrees of motion direction as well as a continuous range of speed without the use of hands via the egocentric computer vision based control we developed. The user wears an egocentric camera and collaborates with the robotic wheelchair by conveying the motion commands with head motions. Compared with previous sip-n-puff, chin-control and tongue-operated solutions to hands-free mobility, this egocentric computer vision based control system provides a more natural human robot interface. Our experiments show that this design is of higher usability and users can quickly learn to control and operate the wheelchair. Besides its convenience in manual navigation, the egocentric camera also supports novel user-robot interaction modes by enabling autonomous navigation towards a detected person or object of interest. User studies demonstrate the usability and efficiency of the proposed egocentric computer vision co-robot wheelchair.

In this paper, an asymmetric cable-driven mechanism is proposed for accurate force control of exoskeleton systems with a compact structure. Inspired by the fact that the required forces in human motions are not symmetric in many cases, a spring-actuator type cable-drive mechanism is adopted, which enables a compact cable routing structure. The joint is connected with the exoskeleton frame through a rotary series elastic mechanism to transmit the desired force to the human user. High performance in force control is achieved by advanced control algorithms, which combine a proportional and differential (PD) controller optimized with a linear quadratic (LQ) method with a disturbance observer (DOB) and a zero phase error tracking (ZPET) feedforward filter. The proposed system was tested for the elbow joint. Experimental results confirmed that the proposed system was able to generate and deliver accurate force to the human user even with external disturbances and modeling uncertainties introduced by human motions.

In this paper, we present an efficient assembly sequence generation method for robot programming, which can reduce the complexity of assembly sequence generation for products within a product family. Today, principle markets for robot assembly automation (e.g., automobile and consumer electronics) have a relatively short product run rate, ranging from six to twelve months. To accommodate this rapidly changing production demand, in most cases, manufacturers design a series of new products within a product family (i.e., a group of products derived from a common product platform) so that they have similar assembly sequences. Seemingly robot programming for a new product within a product family does not require extensive programming adjustments, but it is still complex and manufacturers spend large amount time and money in programming robots for each new product. To solve this problem, we present a new assembly sequence generation method. With a case-based planner, we generate feasible and similar-to-real assembly sequence candidates for a new product from assembly sequences of old products within a product family. Then, we use geometric information extracted from its CAD model to evaluate those candidate sequences. Unlike those used by previous studies, our method can generate an assembly sequence that is more suitable for the concept of a reconfigurable assembly system for general-purpose robots (assembly sequence generation for robot programming); more similar to assembly sequences used in real assembly systems (case-based planning); and more properly evaluated for robot assembly (a CAD model). We apply the proposed method to a toy airplane assembly scenario and demonstrate its feasibility.