ICRA 2015 Papers

Millions of office workplaces are cleaned by a surprisingly small group of cleaning workers every day, however, cleaning companies struggle to recruit enough personnel these days. One solution to this challenge is to schedule available professionals for demanding tasks while relieving them from simpler activities which are transferred to a robotic cleaning assistant. Two of such tasks are floor cleaning and waste disposal which account for 70% of the daily cleaning efforts. This paper presents the world's first autonomous cleaning robot prototype that masters both of these tasks and whose development was accompanied by the advice of a large cleaning company. Besides a detailed description of the overall system and its individual components an evaluation is provided based on real world experiments. The results indicate that both cleaning tasks can be solved at high quality but with potential for increased efficiency to meet the required performance. Hence, the paper concludes with a discussion on measures necessary for the development of a commercial prototype.

MRI compatibility, which often is a requirement for the new medical soft robot projects, greatly reduces available actuation methods and sensors. An example of such project is STIFF-FLOP, which aims to develop a soft silicone manipulator actuated by pressure. The current arm construction and method of actuation cause several undesirable effects, which pose problems for actuation and sensing. In this paper, the authors identify the source of those negative effects and propose improvements over the current construction to eliminate or limit their influence. The new construction concept is tested and compared with the current one. Possible ideas for further development are also proposed.

Navigation of cluttered underwater environments remains to this day a challenging task in mobile robotics. Applying an electric field to a mobile robot's direct environment and measuring perturbations of this field, one is able to detect the presence of foreign objects in close proximity of the system. In addition, one is also able to infer a range of information relative to the detected objects, such as their position or electrical characteristics. Extracting such information from available measures typically requires a model (analytical, numerical or heuristic) descriptive of the relationship from geometry of the scene to measures performed (typically referred to as forward model), or of the inverse relationship (inverse model). In the following, we directly extract one such model from experimental data, and capture a forward model using a neural formalism. Then, using an iterative procedure, we are able to estimate the position of a detected object and assess the degree of confidence one can place on this estimate. Merit of the approach is illustrated using experimental data for a spherical object.

We propose a method to estimate the entire shape of a long flexible needle, suitable for a needle insertion assistant robot. This method bases its prediction on only a small segment of a needle, imaged via ultrasound, after insertion. An algorithm is developed that can segment a needle observed partially in ultrasound images and fully in camera images, returning a polynomial representation of the needle shape after RANSAC processing. The polynomial corresponding to the partial needle observation in ultrasound images is used as the input to a needle-tissue interaction model that predicts the entire needle shape. The needle shape predicted by the model is compared to the segmented needle shape based on camera images to validate the proposed approach. The results show that the entire needle shape can be accurately predicted in tissues of varying stiffness based on observation of parts of the needle in an ultrasound image.

This paper proposes a complete system for robotic sensor placement in initially unknown arbitrary three-dimensional environments. The system uses a novel approach for computing the quality of acquisition of a mobile sensor group in such environments. The quality of acquisition is based on a geometric model of a camera which allows accurate sensor models and simple occlusion computation. The proposed system combines this new metric with a global derivative-free optimization algorithm to find simultaneously the number of sensors and their configuration to sense accordingly the environment. The presented framework compares favourably with current techniques working in two-dimensional environments. Furthermore, simulation and experimental results demonstrate the ability of the system to cope with full three-dimensional environments, a domain still unexplored by previous methods.

This paper describes the development and validation of the Inertial and Range-Enhanced Surgical (IRES) tracker-a novel, noncontact laparoscopic tracking system that may be used as an inexpensive alternative to optical and electromagnetic (EM) tracking systems for tracking surgical instruments. The system is based on the fusion of inertial, magnetic and distance sensing to generate real-time, 6-DOF pose data. Orientation is estimated using a Kalman-filtered attitude-heading reference system (AHRS) and restricted motion at the trocar provides a datum from which position information can be recovered. The IRES tracker was validated within a surgical training box. The results show that the IRES tracker achieves similar performance to an EM tracker with position error as low as 1.25 mm RMS and orientation error <;0.58° RMS along each axis. It also displayed greater precision and superior magnetic interference rejection capabilities. At a fraction of the cost of current laparoscopic tracking methods, the IRES tracking system is a suitable alternative for use in surgical training and skills assessment.

Most current systems capable of robotic object manipulation involve ad hoc assumptions about the order of operations necessary to achieve a task, and usually have no mechanism to predict how earlier decisions will affect the quality of the solution later. Solving this problem is sometimes referred to as combined task and motion planning. We propose that multi-step planning, a technique previously applied in some other domains, is an effective way to address the question of combined task and motion planning. We demonstrate the technique on a complex motion planning problem involving a two-armed robot (PR2) and an articulated object (folding chair) where our planner naturally discovers extra steps that are necessary to satisfy kinematic constraints of the problem. We also propose some further extensions to our algorithm that we believe will make it an extremely powerful technique in this domain.

We present a path-planning algorithm that leverages a multi-scale representation of the environment. The algorithm works in n dimensions. The information of the environment is stored in a tree representing a recursive dyadic partitioning of the search space. The information used by the algorithm is the probability that a node of the tree corresponds to an obstacle in the search space. The complexity of the proposed algorithm is analyzed and its completeness is shown.

The Sat-Tsp language was recently proposed [1] for expressing and solving high-level robotic path planning problems. In this paper we show how different constraints that commonly appear in path planning problems, such as set constraints, counting constraints, and ordering constraints can all be expressed in the Sat-Tsp language. We also show how the language can be used to express multi-robot path planning problems. We evaluate our existing solver approaches on test problems that include a variety of complex constraints and we demonstrate the language through a ROS implementation. We also provide a new approach that reduces the Sat-Tsp language to the generalized traveling salesman problem language. We show that this new approach outperforms our existing approaches on problems that contain one-on-a-set constraints.

In this paper, we present an algorithm to solve the Multi-Robot Persistent Coverage Problem (MRPCP). Here, we seek to compute a schedule that will allow a fleet of agents to visit all targets of a given set while maximizing the frequency of visitation and maintaining a sufficient fuel capacity by refueling at depots. We also present a heuristic method to allow us to compute bounded suboptimal results in real time. The results produced by our algorithm will allow a team of robots to efficiently cover a given set of targets or tasks persistently over long periods of time, even when the cost to transition between tasks is dynamic.

This paper addresses the problem of finding robot configurations to grasp assembly parts during a sequence of collaborative assembly operations. We formulate the search for such configurations as a constraint satisfaction problem (CSP). Collision constraints in an operation and transfer constraints between operations determine the sets of feasible robot configurations. We show that solving the connected constraint graph with off-the-shelf CSP algorithms can quickly become infeasible even for a few sequential assembly operations. We present an algorithm which, through the assumption of feasible regrasps, divides the CSP into independent smaller problems that can be solved exponentially faster. The algorithm then uses local search techniques to improve this solution by removing a gradually increasing number of regrasps from the plan. The algorithm enables the user to stop the planner anytime and use the current best plan if the cost of removing regrasps from the plan exceeds the cost of executing those regrasps. We present simulation experiments to compare our algorithm's performance to a naive algorithm which directly solves the connected constraint graph. We also present a real robot system which uses the output of our planner to grasp and bring parts together in assembly configurations.

Localization of steerable catheters in minimally invasive surgery is critical with respect to patient safety, surgeon manipulation, and procedural efficacy. While there are many potential benefits to patients including shorter recovery times, less tissue trauma, and lower infection rates than traditional surgeries, localization of surgical tools is still an area of much research. Current technology offers several sensory modalities. However, each system has drawbacks which do not provide a clear best practice. This research focuses on incorporating redundant commonplace surgical sensing technologies to reduce the likelihood of errors, failures, or inherent sensor characteristics causing harm to the patient and/or surgeon while providing accurate localization. Dual particle filters are implemented using both a fluoroscopic-like stereo imaging system and an electromagnetic pose sensor for measurement updates in a prototype catheter testbed. A previously developed catheter model is modified to increase accuracy in the particle filter outputs which are combined using a weighted average based on each filter's particle statistics. Experimental results implementing the combined particle filter multi-modality algorithm in feedback control validates the algorithms ability to provide accurate localization in a surgical setting while overcoming sensor limitations and possible failure modes.

Exosuits represent a new approach for applying assistive forces to an individual, using soft textiles to interface to the wearer and transmit forces through specified load paths. In this paper we present a body-worn, multi-joint soft exosuit that assists both ankle plantar flexion and hip flexion through a multiarticular load path, and hip extension through a separate load path, at walking speeds up to 1.79m/s (4.0mph). The exosuit applies forces of 300N in the multiarticular load path and 150N in hip extension, which correspond to torques of 21% and 19% of the nominal biological moments at the ankle and hip during unloaded walking. The multi-joint soft exosuit uses a new actuation approach that exploits joint synergies, with one motor actuating the multiarticular load paths on both legs and one motor actuating the hip extension load paths on both legs, in order to reduce the total system weight. Control is accomplished by an algorithm that uses only a gyroscope at the heel and a load cell monitoring the suit tension, and is shown to adapt within a single step to changes in cadence. Additionally, the control algorithm can create slack in the suit during non-level-ground walking motions such as stepping over obstacles so that the system can be transparent to the wearer when required. The resulting system consumes 137W, and has a mass of 6.5kg including batteries.

We address the problem of human detection from heavy mobile machinery and robotic equipment operating at industrial working sites. Exploiting the fact that workers are typically obliged to wear high-visibility clothing with reflective markers, we propose a new recognition algorithm that specifically incorporates the highly discriminative features of the safety garments in the detection process. Termed Multi-band Hough Forest, our detector fuses the input from active near-infrared (NIR) and RGB color vision to learn a human appearance model that not only allows us to detect and localize industrial workers, but also to estimate their body orientation. We further propose an efficient pipeline for automated generation of training data with high-quality body part annotations that are used in training to increase detector performance. We report a thorough experimental evaluation on challenging image sequences from a real-world production environment, where persons appear in a variety of upright and non-upright body positions.

We propose a multi-robot exploration algorithm that uses adaptive coordination to provide heterogeneous behavior. The key idea is to maximize the efficiency of exploring and mapping an unknown environment when a team is faced with unreliable communication and limited battery life (e.g., with aerial rotorcraft). The proposed algorithm utilizes four states: explore, meet, sacrifice, and relay. The explore state uses a frontier-based exploration algorithm, the meet state returns to the last known location of communication to share data, the sacrifice state sends the robot out to explore without consideration of remaining battery, and the relay state lands the robot until a meeting occurs. This approach allows robots to take on the role of a relay to improve communication between team members. In addition, the robots can “sacrifice” themselves by continuing to explore even when they do not have sufficient battery to return to the base station. We compare the performance of the proposed approach to state-of-the-art frontier-based exploration, and results show gains in explored area. The feasibility of components of the proposed approach is also demonstrated on a team of two custom-built quadcopters exploring an office environment.

We formalize the problem of adapting a demonstrated trajectory to a new start and goal configuration as an optimization problem over a Hilbert space of trajectories: minimize the distance between the demonstration and the new trajectory subject to the new end point constraints. We show that the commonly used version of Dynamic Movement Primitives (DMPs) implement this minimization in the way they adapt demonstrations, for a particular choice of the Hilbert space norm. The generalization to arbitrary norms enables the robot to select a more appropriate norm for the task, as well as learn how to adapt the demonstration from the user. Our experiments show that this can significantly improve the robot's ability to accurately generalize the demonstration.

This paper formulates a new pipeline for automated extrinsic calibration of multi-sensor mobile platforms. The new method can operate on any combination of cameras, navigation sensors and 3D lidars. Current methods for extrinsic calibration are either based on special markers and/or chequerboards, or they require a precise parameters initialisation for the calibration to converge. These two limitations prevent them from being fully automatic. The method presented in this paper removes these restrictions. By combining information extracted from both, platform's motion estimates and external observations, our approach eliminates the need for special markers and also removes the need for manual initialisation. A third advantage is that the motion-based automatic initialisation does not require overlapping field of view between sensors. The paper also provides a method to estimate the accuracy of the resulting calibration. We illustrate the generalisation of our approach and validate its performance by showing results with two contrasting datasets. The first dataset was collected in a city with a car platform, and the second one was collected in a tree-crop farm with a Segway platform.

Conventional motion planners for wheeled vehicles often assume no-slipping and no-skidding conditions and construct motion trajectories in the context of nonholonomic motion planning. However, in some practical situations slipping and skidding cannot be ignored or can even be useful. To take them into account in the construction of planning algorithms, it is important to model the friction force between the tire and the contact plane. In this paper, we first construct a model of the friction force as an extension of the two-dimensional Coulomb model, considering both the slipping conditions and the nonholonomic constraints. Next, we formulate the motion planning problem as a drift parking problem and propose a motion planning strategy combining the nonholonomic planner and the control in the slipping mode. The feasibility and the performance of the proposed strategy are tested under simulation.

We introduce a novel notion for lowering the dimensionality of motion planning problems: Irreducibility. Irreducibility of a configuration space trajectory τ means: We cannot find another configuration space trajectory τ′, such that the swept volume of τ′ is included in the swept volume of τ. The main contribution of our work is twofold: First, we show that motion planning in the space of irreducible trajectories is complete. Second, we show that we can construct reducible subspaces by reasoning about the inherent hierarchical structure of open kinematic chains. Using those theoretical results, we proceed by analytically defining a 7-dimensional irreducible configuration subspace for the humanoid robot HRP-2 under some assumptions. To show its practical importance, we solve a high-dimensional pin-hole problem for HRP-2 from the scratch.