ICRA 2017 论文列表

In this paper, we propose a novel algorithm for planning exploration paths to generate 3D models of unknown environments by using a micro-aerial vehicle (MAV). Our algorithm initially determines a next-best-view (NBV) that maximizes information gain and plans a collision-free path to reach the NBV. Along the path, the MAV explores the greatest unknown area although it sometimes misses minor unreconstructed region, such as a hole or a sparse surface. To cover such a region, we propose an online inspection algorithm that consistently provides an optimal coverage path toward the NBV in real time. The algorithm iteratively refines an inspection path according to the acquired information until the modeling of a specific local area is complete. We evaluated the proposed algorithm by comparing it with other state-of-the-art approaches through simulated experiments. The results show that our algorithm outperforms the other approaches in both exploration and 3D modeling scenarios.

In this paper, we introduce an informative path planning (IPP) framework for active classification using unmanned aerial vehicles (UAVs). Our algorithm uses a combination of global viewpoint selection and evolutionary optimization to refine the planned trajectory in continuous 3D space while satisfying dynamic constraints. Our approach is evaluated on the application of weed detection for precision agriculture. We model the presence of weeds on farmland using an occupancy grid and generate adaptive plans according to information-theoretic objectives, enabling the UAV to gather data efficiently. We validate our approach in simulation by comparing against existing methods, and study the effects of different planning strategies. Our results show that the proposed algorithm builds maps with over 50% lower entropy compared to traditional “lawnmower” coverage in the same amount of time. We demonstrate the planning scheme on a multirotor platform with different artificial farmland set-ups.

This paper shows a method for achieving multi-contact motion for a humanoid robot on a movable object, such as climbing of a stepladder. Recent research has developed methods for achieving multi-contact motion that considers various constraints, such as joint limits, torques, balance constraints, reachability, and collision avoidance. In addition to these constraints, Motion On a Movable Object (MOMO) has the following features: it has to consider an object's balance during the changing of contact points; and it has to handle scenarios where the mass properties of an object are unknown. In this paper, in order to achieve a humanoid robot having MOMO, we propose balance constraints that consider the constraints imposed by an object as well as an online estimation of object's constraints. First, we use object-environment constraints as the robot's constraints, and then we show a method for estimating them based on information provided by the robot's sensors. Next, we show a method for applying the balance constraints to a humanoid motion planner and for executing planned motion with real-time sensor feedback controller. Finally, we evaluate our proposed method through experiments in which a life-sized humanoid robot climbs stepladders that have unknown mass properties.

This paper presents an acoustic localization system for small and low-cost autonomous underwater vehicles (AUVs). Accurate and robust localization for low-cost AUVs would lower the barrier toward multi-AUV research in river and ocean environments. However, these AUVs introduce size, power, and cost constraints that prevent the use of conventional AUV sensors and acoustic positioning systems, adding great difficulty to the problem of underwater localization. Our system uses a single acoustic transmitter placed at a reference point and is acoustically passive on the AUV, reducing cost and power use, and enabling multi-AUV localization. The AUV has an ultra-short baseline (USBL) receiver array that uses one-way travel-time (OWTT) and phased-array beamforming to calculate range, azimuth, and inclination to the transmitter, providing an instantaneous estimate of the vehicle location. This estimate is fed to a particle filter and graph-based smoothing algorithm to generate a consistent AUV trajectory. We describe the complete processing pipeline of our system, and present results based on experiments using a low-cost AUV. To the authors' knowledge, this work constitutes the first practical demonstration of the feasibility of OWTT inverted USBL navigation for AUVs.

An on-line trajectory generation algorithm with time-variant kinematic motion constraints is presented in this paper. The algorithm is an extension of a class of trajectory planning method which is applicable with constant kinematic motion constraints only. The extended approach allows the abrupt change in the value of the physical robot constraints(jerk, acceleration, and velocity) at any time instant and keeps these constraints bounded during the trajectory parameter adaptation. Short computation time enables the real-time usage of the proposed algorithm so that it can update the trajectory at any time taking into account the current robot motion limits. It allows sensor integration in low-level robot motion control, that is, making robots have the capability of reacting to unforeseen sensor events in real time. Simulation results are summarized in the paper.

The performance of a robot system heavily relies on its model. The present paper proposes an efficient online Bayesian regression algorithm based on Gaussian Mixture Model. By using the mixture model of local Gaussian experts, the algorithm decouples global correlation of data and achieves linear computational cost to the size of the local model set. The proposed algorithm also realizes on-line implementation. To manage the size of local model on-the-fly, a strategy of adding and pruning local model based on a probabilistic criteria is proposed. Additionally, a forgetting strategy to treat outliers and non-stationary system is suggested. In the end, the algorithm achieved comparable results to other on-line regression algorithms.

We propose an on-chip micromanipulation method based on mode switching of vibration-induced asymmetric flow. The asymmetric flow can be induced around rotationally asymmetric structures on a microfluidic chip by applying a circular vibration to the chip. Thus, the flow pattern can be switched by changing directions of applied vibrations as clockwise or counter-clockwise. In this study, we applied the switching of flow patterns (e. g., trap mode and transport mode, or trap mode and alignment mode) to change the manipulation modes of microobjects. Furthermore, we demonstrated the proposed method for two applications, local cell concentration and single particle loading. These demonstrations show that the proposed manipulation method can realize versatile on-chip micromanipulations and will contribute to high-throughput and high-reliability cell analysis or diagnosis.

Simultaneous Localization and Mapping (SLAM) is a key stepping stone on the road to truly autonomous robots. SLAM is of particular importance to robots with large motion estimation problems, such as robots operating on the surface of aquatic GPS-denied environments where a paucity of local landmarks complicates SLAM and accurate navigation. Visual sensors have proven to be an effective tool for SLAM generally and have wide applicability, but is vision enough to solve SLAM in this environment, and how important are other sensors including a compass and water column depth to solve SLAM for an aquatic surface vehicle? Here we show that more sensors are almost always helpful in terms of improving SLAM performance in such a situation but that a compass is a particularly useful sensor for SLAM for autonomous surface vehicles; suggesting that a compass is a worthwhile investment for such a robot, and that compass alternatives should be considered when operating an autonomous vehicle in environments that are both GPS and compass-denied.

Finding the Time-Optimal Parameterization of a Path (TOPP) subject to second-order constraints (e.g. acceleration, torque, contact stability, etc.) is an important and well-studied problem in robotics. In comparison, TOPP subject to third-order constraints (e.g. jerk, torque rate, etc.) has received far less attention and remains largely open. In this paper, we investigate the structure of the TOPP problem with third-order constraints. In particular, we identify two major difficulties: (i) how to smoothly connect optimal profiles, and (ii) how to address singularities, which stop profile integration prematurely. We propose a new algorithm, TOPP3, which addresses these two difficulties and thereby constitutes an important milestone towards an efficient computational solution to TOPP with third-order constraints.

In this work, we propose a method to compute the stiffness of flexible joints and its realization in order to let the fingers track a certain predefined trajectory. We refer to tendon-driven, underactuated and passively compliant hands composed of deformable joints and rigid links. Specific stiffness and pre-form shapes can be assigned to the finger joints can be given s such that a single-cable actuation can be used. We firstly define a procedure to determine suitable joints stiffness and then we propose a possible realization of soft joints using rapid prototyping techniques. The stiffness computation is obtained leveraging on the the mechanics of tendon-driven hands and on compliant systems, while for its implementation beam theory has been exploited. We validate the proposed framework both in simulation and with experiments using the robotic Soft-SixthFinger, a wearable robot for grasping compensation in patients with a paretic hand, as a case study. The proposed framework can be used to design the stiffness of the passive joints in several model of underactuated tendon-driven soft hands so to improve their grasping capabilities.

We propose a novel haptic rendering scheme based on passive midpoint integrator (PMI), which is an extension of our prior non-iterative passive mechanical integrator (NPMI) to maximal coordinates for simulation of complex articulated rigid bodies and to multi-point intermittent contact with the linear complementarity problem (LCP) formulation incorporated. The proposed PMI-based haptic rendering then can stably simulate mechanical systems with wide-range of parameters/updaterates (in contrast to semi-implicit Euler integrator), while maintaining losslessness of simple harmonic oscillation (in contrast to implicit Euler integrator), as compared in this paper. Application of this PMI-based haptic rendering is also presented for multi-user virtual co-manipulation of shared rigid object in SE(3) using hand/fingers with multi-point contact over the Internet.

In this paper, we study the effect of mechanical compliance on the impact force of human-robot interactions, more specifically the maximum impact force during a collision. Here we consider two methods of introducing compliance to industrial manipulators: joint compliance and link compliance. To compare their effect on the maximum impact force, we study two designs of a 2D robot link: a rigid link with torsion spring at the joint and a uniform compliant link. The dynamic impact model is based on the Hertz contact model. The results show that the compliant joint solution could produce a larger impact force than that of the compliant link solution if the arm mass is larger than that of the end mass, given the same lateral stiffness and all other inertial parameters (e.g. mass). Simulations and experiment have been done and verified this conclusion. The research demonstrates that the compliant link solution could be a promising approach for addressing safety concerns of human robot interactions.

To accomplish tasks with high accuracy, advanced control strategies that benefit from the knowledge of system parameters are required. However, during operation some of them may change, or be unknown. In this paper, a novel parameter estimation method is proposed, which is based on the conservation of the angular momentum of a space manipulator system in the free-floating mode. The estimated parameters are combinations of spacecraft, manipulator and payload parameters and render the system full dynamics identified and applicable to model-based control. The algorithm requires only measurements of joint angles and rates, and spacecraft attitude and angular velocity. No information about spacecraft and joint accelerations or joint torques, which include substantial noise, is required. Thus, in contrast to other methods using the equations of motion, the proposed method is insensitive to sensor noise. Moreover, it does not require the prior knowledge of any system parameters and can be applied to free-floating systems with more than one manipulators. The application of the proposed method is illustrated by a 3D example.

There are tasks that do not require a controlled motion in all spatial directions. These unused degrees-of-freedom (DOF) make the robot functionally redundant. Traditional methods for redundancy resolution developed for intrinsic redundant robots cannot be used directly for resolving functional redundancy. The functional redundancy is in general not reflected as rows in the Jacobian matrix and therefore, the unused DOFs cannot be mapped into the null-space. In the paper we present a novel approach for the orientation related functional redundancy resolution based on the task space rotation. We define a time-variant task space frame so that one or more frame axes are aligned with the unused directions. This allows that the rows of Jacobian matrix corresponding to functional redundant DOFs are excluded. As the standard quaternion control is not appropriate to control orientation of such functional redundant robots, we propose two control algorithms to control one or two orientation directions. Two examples then show how the proposed control algorithms can be implemented and finally, we present the application of the algorithm on a two-arm robot system.

Perception systems for outdoor robotics have to deal with varying environmental conditions. Variations in illumination in particular, are currently the biggest challenge for vision-based perception. In this paper we present an approach for radiometric characterization of multispectral cameras. To enable spatio-temporal mapping we also present a procedure for in-situ illumination estimation, resulting in radiometric calibration of the collected images. In contrast to current approaches, we present a purely data driven, parameter free approach, based on maximum likelihood estimation which can be performed entirely on the field, without requiring specialised laboratory equipment. Our routine requires three simple datasets which are easily acquired using most modern multispectral cameras. We evaluate the framework with a cost-effective snapshot multispectral camera. The results show that our method enables the creation of quatitatively accurate relative reflectance images with challenging on field calibration datasets under a variety of ambient conditions.

Generic control of wheel-on-leg robots on arbitrary uneven terrains is a challenging task due to the complexity of the robot dynamics, surface interactions, and environmental structures. This paper deals with the control of a wheel-on-leg robot with passive and active internal compliance that enables estimation of wheel-ground interaction forces. The proposed method is based on a continuous state space Q-learning approach that uses the contact forces estimates to learn, through trial and error, the appropriate control policy from a set of predefined behaviors. Without any prior knowledge of the ground geometry, the robot is able to react to unanticipated obstacles. The learned policy proves to be generic and allows the robot to negotiate complex obstacles that had not been considered during learning phase.

This paper presents O-POCO, a visual odometry and SLAM system that makes online decisions regarding what to map and what to ignore. It takes a point cloud from classical SfM and aims to sample it on-line by selecting map features useful for future 6D relocalisation. We use the camera's traveled trajectory to compartamentalize the point cloud, along with visual and spatial information to sample and compress the map. We propose and evaluate a number of different information layers such as the descriptor information's relative entropy, map-feature occupancy grid, and the point cloud's geometry error. We compare our proposed system against both SfM, and online and offline ORB-SLAM using publicly available datasets in addition to our own. Results show that our online compression strategy is capable of outperforming the baseline even for conditions when the number of features per key-frame used for mapping is four times less.

This paper presents a new algorithm for forward kinematics, called Asynchronous Forward Kinematics (AFK). The algorithm has the complexity of O(log n) for updating one joint angle, and O(logn) for obtaining a homogeneous transformation matrix between links. AFK enables computation for efficient forward kinematics under asynchronous sensory data. Moreover, AFK peovides localise computational resources at sensitive joints to the position of the endpoint (e.g. a fingertip), like a root joint. We provide comparative results including computation time, evaluating AFK against the conventional forward kinematics (CFK). The results showed that the computation time is well adequate for real-time computation. Computation time for 100 links takes less than 20 us for 1 query. Moreover, computation time with over 50000 links takes less than 35 us for 1 query.

One key assumption of Belief Space Planning (BSP) is that the data association is known perfectly. In this paper, we relax this assumption in the context of non-myopic planning as well as belief being a Gaussian Mixture Model (GMM). Interestingly, explicit reasoning about the data association within the belief enables our framework to have parsimonious data association, thereby resulting in a scalable solution compared with naïve permutational approaches. Unlike in some of the recent approaches where the number of components in a GMM belief can only be reduced, in our approach this can also go up such as due to perceptual aliasing present in the environment. Furthermore, our approach naturally integrates with inference, providing a unified framework for robust passive and active perception. We demonstrate key aspects of our approach and its comparison with the state of the art on a general abstract domain as well as in a real robot setup.