IROS 2015 论文列表

Towards enhancing the dynamic locomotion and manipulation abilities of bipedal robots in real-world scenarios, a key problem lies in the accurate estimation of the dynamic state of the feet of the robot. In this paper, an approach is presented for estimating the dynamic pose and the internal (body) and external (ground contact) wrenches acting on the individual feet of a bipedal robot fusing haptic (compliant skin), inertial, and force/torque (F/T) measurements. Assuming rigid body dynamics on an individual foot, an Extended Kalman Filter (EKF) is used to combine ankle F/T sensor readings, contact forces computed from a compliant tactile array on the foot sole and accelerometer plus gyroscope measurements, thereby estimating both the state and the external wrenches affecting a foot through a method of state augmentation. Moreover, covariance estimation of the measurement noise was carried out for all sensors, in particular, for the skin, a bayesian-network-based regression method was chosen. The framework was implemented with the iCub humanoid robot under a toppling scenario; the estimated augmented foot state was then used to compute the Foot Rotation Indicator (FRI) trajectory as a validation through prediction of the onset of toppling and instability.

In this paper, we introduce a non-verbal multimodal joint visual attention model for human-robot interaction in household scenarios. Our model combines the bottom-up saliency and depth-based segmentation with the top-down cues such as pointing and gaze to detect the objects of interest according to the user. For generation of the top-down saliency maps, we have introduced novel methods for object saliency, based on the pointing direction as well as the gaze direction. For gaze estimation, a hybrid model has been introduced which automatically selects keypoint-based matching or back-projection based on the textureness of the object model. The combination of different cues ensures reliable object detection and interaction independent of the relative position between the user, robot and objects. Extensive experiments show good detection results in different interaction scenarios as well as in challenging environmental conditions.

Robust object recognition is a crucial ingredient of many, if not all, real-world robotics applications. This paper leverages recent progress on Convolutional Neural Networks (CNNs) and proposes a novel RGB-D architecture for object recognition. Our architecture is composed of two separate CNN processing streams - one for each modality - which are consecutively combined with a late fusion network. We focus on learning with imperfect sensor data, a typical problem in real-world robotics tasks. For accurate learning, we introduce a multi-stage training methodology and two crucial ingredients for handling depth data with CNNs. The first, an effective encoding of depth information for CNNs that enables learning without the need for large depth datasets. The second, a data augmentation scheme for robust learning with depth images by corrupting them with realistic noise patterns. We present state-of-the-art results on the RGB-D object dataset [15] and show recognition in challenging RGB-D real-world noisy settings.

In human-human interaction, three modalities of communication (i.e., verbal, nonverbal, and paraverbal) are naturally coordinated so as to enhance the meaning of the conveyed message. In this paper, we try to create a similar coordination between these modalities of communication in order to make the robot behave as naturally as possible. The proposed system uses a group of videos in order to elicit specific target emotions in a human user, upon which interactive narratives will start (i.e., interactive discussions between the participant and the robot around each video's content). During each interaction experiment, the humanoid expressive ALICE robot engages and generates an adapted multimodal behavior to the emotional content of the projected video using speech, head-arm metaphoric gestures, and/or facial expressions. The interactive speech of the robot is synthesized using Mary-TTS (text to speech toolkit), which is used - in parallel - to generate adapted head-arm gestures [1]. This synthesized multimodal robot behavior is evaluated by the interacting human at the end of each emotion-eliciting experiment. The obtained results validate the positive effect of the generated robot behavior multimodality on interaction.

This paper presents a novel approach to modeling the dynamics of human movements with a grid-based representation. The model we propose, termed as Multi-scale Conditional Transition Map (MCTMap), is an inhomogeneous HMM process that describes transitions of human location state in spatial and temporal space. Unlike existing work, our method is able to capture both local correlations and long-term dependencies on faraway initiating events. This enables the learned model to incorporate more information and to generate an informative representation of human existence probabilities across the grid map and along the temporal axis for intelligent interaction of the robot, such as avoiding or meeting the human. Our model consists of two levels. For each grid cell, we formulate the local dynamics using a variant of the left-to-right HMM, and thus explicitly model the exiting direction from the current cell. The dependency of this process on the entry direction is captured by employing the Input-Output HMM (IOHMM). On the higher level, we introduce the place where the whole trajectory originated into the IOHMM framework forming a hierarchical input structure to capture long-term dependencies. The capabilities of our method are verified by experimental results from 10 hours of data collected in an office corridor environment.

In this paper, we consider several autonomous robots with separate tasks that require coordination, but not a coupling at every decision step. We assume that each robot separately acquires its task, possibly from different providers. We address the problem of multiple robots incrementally acquiring tasks that require their sparse-coordination. To this end, we present an approach to provide tasks to multiple robots, represented as sequences, conditionals, and loops of sensing and actuation primitives. Our approach leverages principles from sparse-coordination to acquire and represent these joint-robot plans compactly. Specifically, each primitive has associated preconditions and effects, and robots can condition on the state of one another. Robots share their state externally using a common domain language. The complete sparse-coordination framework runs on several robots. We report on experiments carried out with a Baxter manipulator and a CoBot mobile service robot.

This paper presents a new taboo-list approach for multi-robot exploration of unknown structured environments, in which agents are implicitly guided in their navigation on a globally shared map. Agents have a local view of their environment, inside which they navigate in a asynchronous manner. When the exploration is complete, agents gather at a rendezvous point. The novelty consists in using a distributed exploration algorithm which is not guided by frontiers to perform this task. Using the Brick&Mortar Improved ant-algorithm as a base, we add robot-perspective vision, variable vision range, and an optimization which prevents agents from going to the rendezvous point before exploration is complete. The algorithm was evaluated in simulation on a set of standard maps.

This paper presents a method for navigating a team of robots in formation in 2D and 3D environments with static and dynamic obstacles. The method is local and computes the optimal parameters for the formation within a neighborhood of the robots, allowing for reconfigurations, when required, by considering a set of target formations. The method consists of first computing the largest collision-free convex polytope in a neighborhood of the robots, followed by a constrained optimization via sequential convex programming where the optimal parameters for the formation are obtained. The robots navigate towards the target collision-free formation with individual local planners that account for their dynamics. The approach is efficient and scalable with the number of robots and performed well in simulations with a large team of quadrators and in experiments with two mobile manipulators carrying a rigid object.

The interaction of a single human with a team of cooperative robots, which collaboratively manipulate an object, poses a great challenge by means of the numerous possibilities of issuing commands to the team or providing appropriate feedback to the human. In this paper we propose a formation-based approach in order to avoid deformations of the object and to virtually couple the human to the formation. Here the human can be interpreted as a leader in a leader-follower formation with the robotic manipulators being the followers. The results of a controllability analysis in such a leader-follower formation suggest that it is beneficial to measure the state of the human (leader) by all physically cooperating manipulators (followers). The proposed approach is evaluated in a full-scale multi-robot cooperative manipulation experiment with humans.

Teams of mobile robots can be deployed in search and rescue missions to explore previously unknown environments. Methods for joint localization and mapping constitute the basis for (semi-)autonomous cooperative action, in particular when navigating in GPS-denied areas. As communication losses may occur, a decentralized solution is required. With these challenges in mind, we designed a submap-based SLAM system that relies on inertial measurements and stereo-vision to create multi-robot dense 3D maps. For online pose and map estimation, we integrate the results of keyframe-based local reference filters through incremental graph SLAM. To the best of our knowledge, we are the first to combine these two methods to benefit from their particular advantages for 6D multi-robot localization and mapping: Local reference filters on each robot provide real-time, long-term stable state estimates that are required for stabilization, control and fast obstacle avoidance, whereas online graph optimization provides global multi-robot pose and map estimates needed for cooperative planning. We propose a novel graph topology for a decoupled integration of local filter estimates from multiple robots into a SLAM graph according to the filters' uncertainty estimates and independence assumptions and evaluated its benefits on two different robots in indoor, outdoor and mixed scenarios. Further, we performed two extended experiments in a multi-robot setup to evaluate the full SLAM system, including visual robot detections and submap matches as inter-robot loop closure constraints.

In our previous work [1] we introduced the Anticipative Kinodynamic Planning (AKP): a robot navigation algorithm in dynamic urban environments that seeks to minimize its disruption to nearby pedestrians. In the present paper, we maintain all the advantages of the AKP, and we overcome the previous limitations by presenting novel contributions to our approach. Firstly, we present a multi-objective cost function to consider different and independent criteria and a well-posed procedure to build a joint cost function in order to select the best path. Then, we improve the construction of the planner tree by introducing a cost-to-go function that will be shown to outperform a classical Euclidean distance approach. In order to achieve real time calculations, we have used a steering heuristic that dramatically speeds up the process. Plenty of simulations and real experiments have been carried out to demonstrate the success of the AKP.

In-vivo and in-vitro micro-interventions by mobile robotic agents require their precise control. Numerous types of microrobotic swimmers have been developed, assuming different peculiar applications, but often suffering from a lack of mobility and robustness, due to their unique propulsion mode. Hence we present in this paper the multi-flagella helical microswimmers that combine complementary propulsion modes for covering different motions and applications. The numerous possibilities of motions make the robots capable of moving rapidly, on long distances and in hard conditions, as expected in biological organisms. Besides, our microswimmers prove to be able of precise targeted binding, reversible binding, and multi-scale cargo transport moving particles from 5 to 30 µm large. Thus the demonstrated skillful multi-flagella helical microswimmers are very promising for future interventions in microfluidic chips and biological organisms, such as cell manipulation, precise drug delivery, minimally invasive surgery.

Reliable manipulation of everyday household objects is essential to the success of service robots. In order to accurately manipulate these objects, robots need to know objects' full 6-DOF pose, which is challenging due to sensor noise, clutters and occlusions. In this paper, we present a new approach for effectively guessing the object pose given an observation of just a small patch of the object, by leveraging the fact that many household objects can only keep stable on a planar surface under a small set of poses. In particular, for each stable pose of an object, we slice the object with horizontal planes and extract multiple cross-section contours. The pose estimation is then reduced to find a stable pose whose contour matches best with that of the sensor data, and this can be solved efficiently by convolution. Experiments on the manipulation tasks in the DARPA Robotics Challenge validate our approach. In addition, we also investigate our method's performance on object recognition tasks raising in the challenge.

This paper presents an innovative hand-held device able to compute stiffness when interacting with a soft object. The device is composed of four linear indenters and a USB camera. The stiffness is computed in real-time, tracking the movements of spherical features in the image of the camera. Those movements relate to the movements of the four indenters when interacting with a soft surface. Since the indenters are connected to springs with different spring constants, the displacement of the indenters varies when interacting with a soft object. The proposed multi-indenting device allows measuring the object's stiffness as well as the pan and tilt angles between the sensor and the surface of the soft object. Tests were performed to evaluate the accuracy of the proposed palpation mechanism against commercial springs of known stiffness. Results show that the accuracy and sensitivity of the proposed device increases with the softness of the examined object. Preliminary tests with silicon show the ability of the sensing mechanism to characterize phantom soft tissue for small indentation. It is noted that the results are not affected by the orientation of the device when probing the surface. The proposed sensing device can be used in different applications, such as external palpation for diagnosis or, if miniaturized, embedded on an endoscopic camera and used in Minimally Invasive Surgery (MIS).

The present paper considers the modeling, control, development and experimental validation of bio-inspired multiarm underwater robotic swimmers actuated by compliant actuating elements, in the context of the soft robotics paradigm. Each one of the swimmer's compliant arms is actuated at its base by a pair of antagonistic compliant shape memory alloy (SMA) springs. The base joint of each such arm displays hysteretic behavior and asymmetries, which are compensated via the modified Prandtl-Ishlinskii (MPI) model of the joint's response, in conjunction with angular position feedback from a potentiometer. This closed-loop control scheme achieves fast and efficient tracking of a sculling joint motion profile. Experimental results based on a pair of such submerged arms, integrated in a catamaran hull, indicate the feasibility of this actuation and control scheme, providing propulsive speeds up to approximately 0.5 arm lengths per second (∼50 mm/sec) and propulsive forces up to 30 mN. The experimental studies presented, regarding the effect of the arm kinematic parameters on propulsive speed and force, are in qualitative agreement with previous results of our group for rigid-actuator multi-arm underwater swimmers.

We propose the Stochastic Multi-Robot Persistent Coverage Problem (SMRPCP) and correspondant methodology to compute an optimal schedule that enables a fleet of energy-constrained unmanned aerial vehicles to repeatedly perform a set of tasks while maximizing the frequency of task completion and preserving energy reserves via recharging depots. The approach enables online modeling of uncertain task costs and yields a schedule that adapts according to an evolving energy expenditure model. A fast heuristic method is formulated that enables online generation of a schedule that concurrently maximizes task completion frequency and avoids the risk of individual robot energy-depletion and consequential platform failure. Failure mitigation is introduced through a recourse strategy that routes robots based on acceptable levels of risk. Simulation and experimental results evaluate the efficacy of the proposed methodology and demonstrate online system-level adaptation due to increasingly certain costs models acquired during the deployment execution.

The improvement of collision avoidance for vessels in close range encounter situations is an important topic for maritime traffic safety. Typical approaches generate evasive trajectories or optimise the trajectories of all involved vessels. The idea of this work is to validate these trajectories related to guaranteed motion safety, which means that it is not sufficient for a trajectory to be collision-free, but it must additionally ensure that an evasive manoeuvre is performable at any time. An approach using the distance and the evolution of the distance to the other vessels is proposed. The concept of Inevitable Collision States (ICS) is adopted to identify the states for which no evasive manoeuvre exist. Furthermore, it is implemented into a collision avoidance system for recreational crafts to demonstrate the performance.

This paper presents the method to retarget human motion. The method can evaluate the ability of the preservation of the original characteristics of human motion data. It enables to compute the joint trajectories of the human corresponding with the retargeted ones of the robot at the same time, by utilizing the geometric identification technique. The obtained trajectories of a human are the solution to minimize the cost function about motion reproduction. The proposed method is efficient for such applications that the robot needs to mimic human motion without modifying the detailed features of the original movement of each body segment. The results of the retargeted motions to a humanoid robot are shown.

This paper proposes a novel motion planning approach that exploits the concept of synergies (correlations) between degrees of freedom, extending it to the velocity space and calling them first-order synergies. An automatic partition method is defined to optimally divide the configuration space into cells where first-order synergies are significantly different. Using this partition, an algorithm that tends to grow a tree by extending the branches in the directions determined by the the first-order synergies of the cell where the leaf to be grown lies is introduced and called FOS-RRT. This allows the natural expansion of the tree along the directions determined by the data used to define the synergies. 2D examples illustrate the performance of the proposed approach, which is particularly attractive for potential applications in human-like robots using human synergies.