ICRA 2019 论文列表

This paper presents the design, fabrication, and operation of compound micromachines powered by acoustic streaming. The machine components were directly incorporated around pillars serving as shafts without further assembly steps using a single-step in situ polymerization process controlled by a programmable projector. Two strategies were presented for harvesting acoustic energy using sharp-edged structures. The first method is based on on-board pumping of fluids and the second method involves engineering of rotors. The implementation of these strategies resulted in the construction of microscale turbines and engines that can be coupled to gear trains for adaptable transmission of mechanical power. We provide a number of further improvements that may together lead to development of compact yet powerful robotic manipulation systems inside microfluidic devices.

This paper suggests reflections can be practically useful if they are included in planning for collision capable robot platforms. By modifying a proven strategy for navigation with reflections we maintain global convergence results and reach the goal in less time. An algorithm for identifying reflection surfaces for a given cell decomposition is reported. Baseline and reflected scenarios are compared for two different cell decompositions. Omnipuck, a reflection capable omnidirectional robot meant to store and release impact energy, is used to obtain experimental results and draw conclusions for future work.

Minimally Invasive Surgery (MIS) is one of the most successful applications of surgical robots. Although the introduction of robotic technology has brought a number of benefits, further advancements in MIS are limited by the size and bending radius of instruments. In this paper, we present a compliant four degree-of-freedom manipulator that consists of elastic elements with partly thinner structures. The proposed mechanism allows the elastic element to deform locally, thus minimizing its bending radius while the low number of mechanical parts greatly contributes to its compactness. This paper describes the design strategy, optimization method using FEA, prototype implementation, and evaluations. The evaluations reveal high accuracy and repeat accuracy, which are key elements for robotic instruments in MIS. Further, the prototype is able to exert sufficient force and it is possible to perform a simulated needle insertion task using the manipulator, demonstrating the feasibility of the proposed mechanism.

The current paper proposes a control methodology for ensuring safety during human-robot interaction based on a compliant sensor covering the robot links as a lightweight shell. The method can be used with existing robots without the need for mechanical redesign. To assess the behaviour of the proposed control law, the controller is analysed using a linear robot model. Stability analysis is performed and requirements on the controller parameters are derived. The effect of the controller parameters on the perceived impedance and the maximum safe operating velocity of the robot are determined via the linear model. The adverse impact of dry friction is analysed in simulation and methods are developed to mitigate the effects. The controller is implemented on a 1 DoF robotic joint and the results are compared to those of a traditional admittance control law, demonstrating comparable transient response while maintaining a simple control structure and decreased risk of instability.

Small aerial robots usually face a common challenge: they can only fly for a short time due to their limited onboard energy supply. To tackle this issue, one promising solution is to endow flying robots with perching capability so that they can perch or land on walls, trees, or power lines to rest or recharge. Such perching capability is especially useful for monitoring-related tasks since the robot can maintain a desired height for monitoring without flying. One of the major challenges for perching is to design a light-weight and energy-efficient perching mechanism. In this paper, we present a 3D-printed compliant bistable gripper which is easy to close, stable to hold, and easy to adjust for a palm-size quadcopter to perch on cylindrical objects. If installed on the bottom of aerial robots, it can also be used for aerial grasping. The gripper can be directly activated by the impact force during contact to switch from open state to closed state. It can also hold the quadcopter safely since the required force to open the gripper is larger than the robot weight. We analyze the required forces for closing and opening to provide design guidelines for the mechanism. Experimental results show that the designed gripper can successful make the quadcopter perch on cylinders as well as grasp objects.

A simultaneous robotic footprint and sensor coverage planning scheme is proposed to efficiently detect all the unknown targets with range sensors and cover the targets with the robot's footprint in a structured environment. The proposed online Sensor-based Complete Coverage (online SCC) planning minimizes the total traveling distance of the robot, guarantees the complete sensor coverage of the whole free space, and achieves near-optimal footprint coverage of all the targets. The planning strategy is applied to a crack-filling robotic prototype to detect and fill all the unknown cracks on ground surfaces. Simulation and experimental results are presented that confirm the efficiency and effectiveness of the proposed online planning algorithm.

A geometry-based analytic attitude estimation using a rate measurement and measurement of a single reference vector has been recently proposed. Because rigid body attitude estimation is a fundamentally nonlinear problem, the geometry-based method does not contain errors consequent to linearization approximations. A critical source of residual error in the geometric solution is on account of the noise and bias in the vector and rate measurements. A methodical perturbation analysis of the attitude estimate is performed in this paper that reveals the effects of measurement noise and bias, and provides means to compensate for, or filter out, such errors. Application of the filter and compensation provides better attitude estimation than a standard Extended Kalman filter using an optimal Kalman gain. The geometric method is first verified in experiments and then simulation results are provided that validate the better performance of the geometric attitude and bias estimator.

Designing resource-collection algorithms for relatively simple robots that are effective given the noise and uncertainty of the real world is a challenge in swarm robotics. This paper describes the performance of two algorithms for collective robot foraging: the stochastic central-place foraging algorithm (CPFA) and the distributed deterministic spiral algorithm (DDSA). With the CPFA, robots mimic the foraging behaviors of ants; they stochastically search for targets and share information to recruit other robots to locations where they detect multiple targets. With the DDSA, robots travel along pre-planned spiral paths; robots detect the nearest targets first and, in theory, guarantee eventual complete coverage of the arena with minimal overlap. We implemented both algorithms and compared their performance in a Gazebo simulation and in physical robots in a large outdoor arena. In a realistic Gazebo simulation, the DDSA outperforms the CPFA. However, in real-world experiments with obstacles, collisions, and errors, the movement patterns of robots implementing the DDSA become visually indistinguishable from the CPFA. The CPFA is less affected by noise and error, and it performs as well as, or better than, the DDSA. Physical experiments change our conclusion about which algorithm has the best performance, emphasizing the importance of systematically comparing the performance of swarm robotic algorithms in the real world.

Physics engines play an important role in robot planning and control; however, many real-world control problems involve complex contact dynamics that cannot be characterized analytically. Most physics engines therefore employ approximations that lead to a loss in precision. In this paper, we propose a hybrid dynamics model, simulator-augmented interaction networks (SAIN), combining a physics engine with an object-based neural network for dynamics modeling. Compared with existing models that are purely analytical or purely data-driven, our hybrid model captures the dynamics of interacting objects in a more accurate and data-efficient manner. Experiments both in simulation and on a real robot suggest that it also leads to better performance when used in complex control tasks. Finally, we show that our model generalizes to novel environments with varying object shapes and materials.

We propose a novel approach to Combined Task and Motion Planning (TAMP) under partial observability. Previous optimization-based TAMP methods [1][2] compute optimal plans and paths assuming full observability. However, partial observability requires the solution to be a policy that reacts to the observations that the agent receives. We consider a formulation where observations introduce additional branching in the symbolic decision tree. The solution is now given by a reactive policy on the symbolic level together with a path tree that describes the branchings of optimal motion depending on the observations. Our method works in two stages: First, the symbolic policy is optimized using approximate path costs estimated from independent optimizations of trajectory pieces. Second, we fix the best symbolic policy and optimize a joint trajectory tree. We test our approach on object manipulation and autonomous driving examples. We also compare the algorithm's performance to a state-of-the-art TAMP planner in fully observable cases.

The sense of touch is essential for reliable mapping between the environment and a robot which interacts physically with objects. Presumably, an artificial tactile skin would facilitate safe interaction of the robots with the environment. In this work, we present our color-coded tactile sensor, incorporating plastic optical fibers (POF), transparent silicone rubber and an off-the-shelf color camera. Processing electronics are placed away from the sensing surface to make the sensor robust to harsh environments. Contact localization is possible thanks to the lower number of light sources compared to the number of camera POFs. Classical machine learning techniques and a hierarchical classification scheme were used for contact localization. Specifically, we generated the mapping from stimulation to sensation of a robotic perception system using our sensor. We achieved a force sensing range up to 18 N with the force resolution of around 3.6 N and the spatial resolution of 8 mm. The color-coded tactile sensor is suitable for tactile exploration and might enable further innovations in robust tactile sensing.

This paper describes CoLo - a performance evaluation system for two-dimensional cooperative localization algorithms. The system consists of a physical experiment (CoLo-PE) for data collection and a software analysis tool (CoLo-AT) using real-world datasets to evaluate the performances of users’ cooperative localization algorithms. This paper details the design and operation of the physical experiment (CoLo-PE) and discusses the functionalities and uses of the software analysis tool (CoLo-AT) for algorithm evaluation. Specifically, CoLo allows researchers to conveniently add their cooperative localization algorithms and test them extensively on different real-world datasets with various settings. CoLo is available at https://git.uclalemur.com/billyskc/CoLo.

Robust autonomous navigation is one of the most important aspects in the acceptance of social robots by elderly users. Traditional model-based navigation techniques provide a stable theoretical and practical foundation for autonomous operation in domestic environments, but fall short in achieving human-like, acceptable behaviour while still being able to robustly navigate cluttered environments. In this work, we propose ClusterNav, a novel learning-based technique for navigation. Our technique consists of teaching the robot how it should move in the environment in a human-like manner, capturing key features of this demonstration in a geometric representation of the environment. This representation is then used to generate new trajectories for execution, allowing the robot move in an acceptable manner. We have tested our technique in a real environment in an elderly care facility, comparing it with the traditional model-based approach. Tests involved both expert and non-expert users teleoperating the robot. Results show that ClusterNav is capable of navigating the environment, achieving better similarity with the reference trajectories and higher execution speed when compared to the model-based approach.

We consider the problem of transferring policies to the real world by training on a distribution of simulated scenarios. Rather than manually tuning the randomization of simulations, we adapt the simulation parameter distribution using a few real world roll-outs interleaved with policy training. In doing so, we are able to change the distribution of simulations to improve the policy transfer by matching the policy behavior in simulation and the real world. We show that policies trained with our method are able to reliably transfer to different robots in two real world tasks: swing-peg-in-hole and opening a cabinet drawer. The video of our experiments can be found at https://sites.google.com/view/simopt.

Walking gaits generated using Model Predictive Control (MPC) is widely used due to its capability to handle several constraints that characterize humanoid locomotion. The use of simplified models such as the Linear Inverted Pendulum allows to perform computations in real-time, giving the robot the fundamental capacity to replan its motion to follow external inputs (e.g. reference velocity, footstep plans). However, usually the MPC does not take into account the current state of the robot when computing the reference motion, losing the ability to react to external disturbances. In this paper a closed-loop MPC scheme is proposed to estimate the robot's real state through Simultaneous Localization and Mapping (SLAM) and proprioceptive sensors (force/torque). With the proposed control scheme it is shown that the robot is able to react to external disturbances (push), by stepping to recover from the loss of balance. Moreover the localization allows the robot to navigate to target positions in the environment without being affected by the drift generated by imperfect open-loop control execution. We validate the proposed scheme through two different experiments with a HRP-4 humanoid robot.

Fig. 1.Generating predictions of a future for a pedestrian attempting to cross the street. We pick out two key frames from the (a) input sequence and the (b) ground truth sequence, 16 frames apart. Image (c) shows our prediction at the same time instant as the ground truth.We explore prediction of urban pedestrian actions by generating a video future of the traffic scene, and show promising results in classifying pedestrian behaviour before it is observed. We compare several encoder-decoder network models that predict 16 frames (400-600 milliseconds of video) from the preceding 16 frames. Our main contribution is a method for learning a sequence of representations to iteratively transform features learnt from the input to the future. Then we use a binary action classifier network for determining a pedestrian's crossing intent from predicted video. Our results show an average precision of 81%, significantly higher than previous methods. The model with the best classification performance runs for 117 ms on commodity GPU, giving an effective look-ahead of 416 ms.

This paper addresses the circular formation and concentric formation stabilization problem of kinematic unicycles. We design distributed control laws driving unicycles to converge to a common circle at the first stage and a velocity control law enabling unicycles to achieve a specific formation on the circle at the second stage. We also achieve the concentric formation by dividing unicycles into groups and design distributed control laws reinforcing each group at a desired circular orbit from the stationary center. We provide analysis to show that both the circular and concentric formations are asymptotically stable using set stabilization theory. Typical examples are selected to demonstrate and support the theoretical results.

In this paper, we introduce a new class of submillimeter robot (ChevBot) for microfactory applications in dry environments, powered by a 532 nm laser beam. ChevBot is an untethered microrobot propelled by a thermal Micro Electro Mechanical (MEMS) actuator upon exposure to the laser light. Novel models for opto-thermal-mechanical energy conversion are proposed to describe the microrobot's locomotion mechanism. First, an opto-thermal simulation model is presented which is experimentally validated with static displacement measurements with microrobots tethered to the substrate. Then, stick and slip motion of the microrobot was predicted using a dynamic extension of our simulation model, and experiments were conducted to validate this model in one dimension. Promising microrobot designs were fabricated on a silicon on insulator (SOI) wafer with 20 μm device layer and a dimple was assembled at the bottom to initiate directional locomotion on a silicon substrate. Validation experiments demonstrate that exposure to laser power below 2W and repetition frequencies below 60 kHz can generate actuator displacements of a few microns, and 46 μm/s locomotion velocity.

Mitigating potential hazards for planetary rovers posed by soft soils requires testing in representative environments such as with Martian soil simulants in reduced gravity. This work describes the experimentation, methods, and results of a rover-soil visualization technique that produced rich datasets of reduced gravity wheel-terrain interaction. The activities are linked to the upcoming ExoMars space mission, through the use of ExoMars wheel prototype and Martian soil simulant in simulated Martian gravity produced in parabolic flights. The results indicate that, with wheel normal load held equal between experiments, the amount of soil mobilized by wheel-soil interaction increases as gravity decreases. Moreover, the amount of soil mobilized is more sensitive to slip in lower gravity. The results of the visualization analysis suggest a deterioration in the soil resistance and weaker soil bonding at lower gravities, which undermines the rover mobility by reducing the net traction. The results have important implications regarding the practice of using a reduced-mass rover on Earth to assess the performance of a full-mass rover in similar soil on an extraterrestrial surface.