ICRA 2017 Papers

We propose a coordination mechanism to avoid inter-robot collisions when the robots' paths overlap with each other. Our proposed coordination technique uses a weighted bipartite matching-based formulation to solve this problem. Initially, each robot is given a unique goal location. But the robots do not know about other robots' planned paths until they come within each other's communication ranges. When two or more robots get within an unsafe distance, they coordinate their paths to avoid collisions with each other. The objective of the coordination mechanism is to plan a modified path for each coordinating robot (if needed) so that all the robots can reach their goal locations without collision with each other and also while reducing the extra distance introduced while resolving path conflicts. We have proved the correctness and convergence of our coordination strategy. Our experimental results show that the robots using our proposed strategy travel up to 4.2 times less than a comparable heuristic approach.

From being soft, flexible and producing movement by contracting, soft linear actuators are said to have muscle-like properties. Due to these similarities, they are often called “artificial muscle actuator.” However, the strain produced by these actuators is generally insufficient to be utilized in a large range of applications. Some solutions have been developed, but they sacrifice force to increase the displacement. Meanwhile, the force produced by skeletal muscles increases as it contracts due to its working principle, which is based on the “sliding filament mechanism.” The limitations of soft linear actuators could be overcome by mimicking the contraction process of skeletal muscles. Two types of muscle-inspired robotic joint mechanisms based on the sliding filament mechanism principle are proposed in this work. The mechanisms can be operated using any type of soft linear actuators as well as traditional actuators or motors, and this work realizes the implementation using shape memory alloy wires and 3D printed mechanical parts. The feasibility of both proposed mechanisms, and their capabilities were experimentally verified.

Bone milling is widely used in many hard tissue surgical procedures, and the main concern is the mechanical damage to some important tissues induced by the high-speed rotating tool. In this study, the behavior of the human auditory system is analyzed. Following this, a commercially available microphone is mounted on the robot arm and then measures the sound generated from bone milling. Inspired by the bandpass filtering in the cochlea, the recorded sound pressure signal is decomposed into a set of subband signals by wavelet packet transform. Inspired by encoding and perception mechanisms in human auditory system, the average amplitude of the wavelet coefficients in each subband is calculated and inputted to a self-organizing feature map so as to classify different milling states. In order to increase the robustness to noise, the sum of the Manhattan distances between all winning neurons is calculated to select the optimum dimension of the map. The experimental results in milling in vitro porcine spines prove that the proposed method can determine which type of tissue is being cut when the suction noise exists, and the success classification rate is no less than 85%. Therefore, the safety of the robot-assisted milling surgery is improved.

Aquatic animal movement results from a complex balance between muscular actuation, swimmer's inertia, damping, and stiffness; as well as, the effects from the fluid environment. Most aquatic animals utilize undulatory propulsion methods during swimming. Propulsion mode transition involves a variation of these parameters, and to better investigate the variation of these parameters during propulsion mode switching, and provide guidance for swimming robot design, we studied propulsion mechanism of undulation locomotion by combining biological investigation, mathematical simulation and experimental validation. A modular robot platform, with assembling function, was built based on the obtained biological features to realize the corresponding propulsion methods. Then a modular dynamic modeling method was proposed to simulate robot locomotion using a CPG based algorithm and a PD control method, further revealing the underlying mechanism for undulatory locomotion. Finally, experiments were conducted using the robotic platform to validate the found conclusions as well as enhance the propulsion mechanism of undulatory motion, providing a generic guidance for swimming robot design.

This paper studies the synthesis of between-leg coupling schemes for passively-adaptive non-redundant legged robots. Highly actuated legged robots can arbitrarily locate their feet relative to their bodies through active control, but often wind up kinematically over-constrained following ground contact, requiring complex redundant control for stable locomotion. The use of passive sprung joints can provide some minimal passive adaptability to terrain, but it is limited to relatively low terrain variability due to practical travel limits. In this paper, using a 4-RR platform as case study, we show that implementing parallel adaptive couplings between legs of a stance platform can yield substantial passive adaptability to rough terrain while still ensuring that the body is fully constrained in stance. This study uses screw theory-based mobility analysis methods to determine the number of constraints required to control the stance platform. Several coupling schemes are then considered and evaluated through a simulation of their stance capabilities over arbitrary terrain. An experimental validation of these simulation results is presented; it demonstrates the viability of the proposed scheme for passive adaptability.

This paper considers the problem of controlling a formation of quadrotor UAVs equipped with onboard cameras with the goal of maintaining bearing rigidity during motion despite the presence of several sensing constraints, that is, minimum/maximum range, limited camera field of view, and possible occlusions caused by the agents of the formation. To this end, a decentralized gradient-based control action is developed, based on a suitable ‘degree of infinitesimal rigidity’ linked to the spectral properties of the bearing rigidity matrix. The approach is then experimentally validated with five quadrotor UAVs.

Programming by Demonstration allows to transfer skills from human demonstrators to robotic systems by observation and reproduction. One aspect that is often overlooked is that humans show different trajectories over multiple demonstrations for the same task. Observed movements may be more precise in some phases and more diverse in others. It is well-known that the variability of the execution carries important information about the task. Therefore, we propose a Bayesian approach to model uncertainties from training data and to infer them in regions with sparse information. The approach is validated in simulation, where it shows higher precision than existing methods, and a robotic experiment with variance based impedance adaptation.

Active policy search combines the trial-and-error methodology from policy search with Bayesian optimization to actively find the optimal policy. First, policy search is a type of reinforcement learning which has become very popular for robot control, for its ability to deal with complex continuous state and action spaces. Second, Bayesian optimization is a sample efficient global optimization method that uses a surrogate model, like a Gaussian process, and optimal decision making to carefully select each sample during the optimization process. Sample efficiency is of paramount importance when each trial involves the real robot, expensive Monte Carlo runs, or a complex simulator. Black-box Bayesian optimization generally assumes a cost function from a stationary process, because nonstationary modeling is usually based on prior knowledge. However, many control problems are inherently nonstationary due to their failure conditions, terminal states and other abrupt effects. In this paper, we present a kernel function specially designed for Bayesian optimization, that allows nonstationary modeling without prior knowledge, using an adaptive local region. The new kernel results in an improved local search (exploitation), without penalizing the global search (exploration), as shown experimentally in well-known optimization benchmarks and robot control scenarios. We finally show its potential for the design of the wing shape of a UAV.

We consider the problem of building accurate and descriptive 3D occupancy maps of an environment from sparse and noisy range sensor data. We seek to accomplish this task by constructing a predictive model online and inferring the occupancy probability of regions we have not directly observed. We propose a novel algorithm leveraging recent advances in data structures for mapping, sparse kernels, and Bayesian nonparametric inference. The resulting inference model has several desirable properties in comparison to existing methods, including speed of computation, the ability to be recursively updated without approximation, and consistency between batch and online inference. The method also reverts to the use of a specified prior state when insufficient relevant training data exist to predict the occupancy probability of a query point, a property which is attractive for motion planning and exploration applications with mobile robots.

This paper presents a fire heading estimation for solving the autonomous navigation problem of a firefighting robot in smoke-filled indoor fire environment. In smoke-filled fire environments, firefighters and firefighting robots experience difficulty maintaining direction while finding the fire source. To solve this, the statistical texture features in thermal images were analyzed and fused by using Bayesian estimation to compute the vertical and horizontal fire heading. For its validation, a large-scaled test-bed was built with a hallway and two rooms, with one of the rooms having a real size fire generating dense and dark smoke. The proposed method probabilistically computed the fire-heading toward the entrance of the hallway then guided the robot to the room with the actual fire, all while navigating in a smoke-filled situation. The experimental results have demonstrated the effectiveness of this method in indoor fire environments.

In this research, a small humanoid robot and a bicycle of comparable size are constructed. Like the human rider, the robot is designed to pedal, balance and steer the bicycle. We particularly focus on the design of control system for the robot to balance and steer the bicycle using the handlebar. The control system is novel that it is capable of estimating the uncertain center of gravity of the robot-bicycle system and then incorporating such an estimation to enhance control performance. The control system design is based on a general control framework which can establish asymptotic stability under unknown measurement biases. The stability of the control system is theoretically proved and a systematic procedure to compute the control parameters is given. Both simulations and experiments verify that the proposed controller can automatically counteract the mass imbalance in the system and allow the robot to perform straight-line steering.

This paper investigates how a robot that can produce contingent listener response, i.e., backchannel, can deeply engage children as a storyteller. We propose a backchannel opportunity prediction (BOP) model trained from a dataset of children's dyad storytelling and listening activities. Using this dataset, we gain better understanding of what speaker cues children can decode to find backchannel timing, and what type of nonverbal behaviors they produce to indicate engagement status as a listener. Applying our BOP model, we conducted two studies, within- and between-subjects, using our social robot platform, Tega. Behavioral and self-reported analyses from the two studies consistently suggest that children are more engaged with a contingent backchanneling robot listener. Children perceived the contingent robot as more attentive and more interested in their story compared to a non-contingent robot. We find that children significantly gaze more at the contingent robot while storytelling and speak more with higher energy to a contingent robot.

This paper presents a practical swing-angle estimation method for slung load operations of the multi-rotor unmanned aerial vehicle (UAV), which is essential to maintain the safety during the operation. In order not to rely on extra sensors for monitoring the swing angle, the proposed method in this paper offers an autonomous swing-angle estimation using only an inertial measurement unit (IMU) and a single load cell attached to the slung load. The disturbance observer (DOB) derived external force estimation is performed to estimate the swing angle. The unique structure of the proposed DOB-based disturbance force estimation technique utilizes the IMU data only. Both simulation and actual experiment are performed to validate the feasibility of the proposed algorithm.

In autonomous suturing with a surgical robot, needle shape, diameter, and path are critical parameters that directly affect suture depth and tissue trauma. This paper presents an optimization-based approach to specify these parameters. Given clinical suturing guidelines, a kinematic model of needle-tissue interaction was developed to quantify suture parameters and constraints. The model was further used to formulate constant curvature needle path planning as a nonlinear optimization problem. The inputs of the optimization include the tissue geometry, surgeon defined entry/exit points, and optimization weighting factors. The outputs are the needle geometry and suggested path. Off-line simulations were used to evaluate the accuracy and performance of the proposed model, and to determine optimized needle geometry and path for several clinically relevant input sets. The output and the optimization results were confirmed experimentally with the Raven II surgical system. The proposed needle path planning algorithm guarantees minimal tissue trauma and complies with a wide range of suturing requirements.

Robot-assisted minimally invasive surgery can benefit from the automation of common, repetitive or well-defined but ergonomically difficult tasks. One such task is the scanning of a pick-up endomicroscopy probe over a complex, undulating tissue surface to enhance the effective field-of-view through video mosaicing. In this paper, the da Vinci® surgical robot, through the dVRK framework, is used for autonomous scanning and 2D mosaicing over a user-defined region of interest. To achieve the level of precision required for high quality mosaic generation, which relies on sufficient overlap between consecutive image frames, visual servoing is performed using a combination of a tracking marker attached to the probe and the endomicroscopy images themselves. The resulting sub-millimetre accuracy of the probe motion allows for the generation of large mosaics with minimal intervention from the surgeon. Images are streamed from the endomicroscope and overlaid live onto the surgeons view, while 2D mosaics are generated in real-time, and fused into a 3D stereo reconstruction of the surgical scene, thus providing intuitive visualisation and fusion of the multi-scale images. The system therefore offers significant potential to enhance surgical procedures, by providing the operator with cellular-scale information over a larger area than could typically be achieved by manual scanning.

Bridge condition assessment is important to maintain the quality of highway roads for public transport. Bridge deterioration with time is inevitable due to aging material, environmental wear and in some cases, inadequate maintenance. Non-destructive evaluation (NDE) methods are preferred for condition assessment for bridges, concrete buildings, and other civil structures. Some examples of NDE methods are ground penetrating radar (GPR), acoustic emission, and electrical resistivity (ER). NDE methods provide the ability to inspect a structure without causing any damage to the structure in the process. In addition, NDE methods typically cost less than other methods, since they do not require inspection sites to be evacuated prior to inspection, which greatly reduces the cost of safety related issues during the inspection process. In this paper, an autonomous robotic system equipped with three different NDE sensors is presented. The system employs GPR, ER, and a camera for data collection. The system is capable of performing real-time, cost-effective bridge deck inspection, and is comprised of a mechanical robot design and machine learning and pattern recognition methods for automated steel rebar picking to provide realtime condition maps of the corrosive deck environments.

Predominately, robotic construction is applied as prefabrication in structured indoor environments with standard building materials. Our work, on the other hand, focuses on utilizing irregular materials found on-site, such as rubble and rocks, for autonomous construction. We present a pipeline that detects randomly placed objects in a scene that are used by our next best stacking pose searching method employing gradient descent with a random initial orientation, exploiting a physics engine. This approach is validated in an experimental setup using a robotic manipulator by constructing balancing vertical stacks without mortars and adhesives. We show the results of eleven consecutive trials to form such towers autonomously using four arbitrarily in front of the robot placed rocks.

This work introduces a novel hybrid control architecture for a hexapod platform (Weaver), making it capable of autonomously navigating in uneven terrain. The main contribution stems from the use of vision-based exteroceptive terrain perception to adapt the robot's locomotion parameters. Avoiding computationally expensive path planning for the individual foot tips, the adaptation controller enables the robot to reactively adapt to the surface structure it is moving on. The virtual stiffness, which mainly characterizes the behavior of the legs' impedance controller is adapted according to visually perceived terrain properties. To further improve locomotion, the frequency and height of the robot's stride are similarly adapted. Furthermore, novel methods for terrain characterization and a keyframe based visual-inertial odometry algorithm are combined to generate a spatial map of terrain characteristics. Localization via odometry also allows for autonomous missions on variable terrain by incorporating global navigation and terrain adaptation into one control architecture. Autonomous runs on a testbed with variable terrain types illustrate that adaptive stride and impedance behavior decreases the cost of transport by 30 % compared to a non-adaptive approach and simultaneously increases body stability (up to 88 % on even terrain and by 54 % on uneven terrain). Weaver is able to freely explore outdoor environments as it is completely free of external tethers, as shown in the experiments.

Autonomous control of magnetically-actuated miniature robots enables greater versatility and complexity in function but has so far been a challenge to implement. In this paper, we present closed-loop position feedback control of a miniature origami robot utilizing its integrated magnet and an array of Hall effect sensors, enabling the robot's actuation, detection, and locomotion to be initiated from outside its body. An array of 33 Hall effect sensors arranged in repeated triangles cover a range of 60 mm by 75 mm, enabling position detection of the robot with average error of 0.995±0.520 mm. The robot's speed response to applied magnetic field was characterized, and a controller was designed to actuate the robot dependably. We demonstrate autonomous movement of the robot along preplanned paths and the viability of magnetic detection and actuation.