ICRA 2019 论文列表

Piecewise affine (PWA) systems are widely used to model highly nonlinear behaviors such as contact dynamics in robot locomotion and manipulation. Existing control techniques for PWA systems have computational drawbacks, both in offline design and online implementation. In this paper, we introduce a method to obtain feedback control policies and a corresponding set of admissible initial conditions for discrete-time PWA systems such that all the closed-loop trajectories reach a goal polytope, while a cost function is optimized. The idea is conceptually similar to LQR-trees [1], which consists of 3 steps: (1) open-loop trajectory optimization, (2) feedback control for computation of “funnels” of states around trajectories, and (3) repeating (1) and (2) in a way that the funnels are grown backward from the goal in a tree fashion and fill the state-space as much as possible. We show PWA dynamics can be exploited to combine step (1) and (2) into a single step that is tackled using mixed-integer convex programming, which makes the method suitable for dealing with hard constraints. Illustrative examples on contact-based dynamics are presented.

Designing robot controllers that correctly react to changes in the environment is a time-consuming and error-prone process. An alternative is to use “correct-by-construction” synthesis approaches to automatically generate controller designs from high-level specifications. In particular, Generalized Reactivity(l) or GR(1) specifications are well-suited to express specifications for robots that must act in dynamic environments, and approaches to generate controller designs from GR(1) specifications are highly computationally efficient. Toward that end, this paper presents Salty, a domain-specific language for GR(1) specifications. While tools exist to synthesize system designs from GR(1) specifications, Salty makes such specifications easier to write and debug by supporting features such as richer input and output types, user-defined macros, common specification patterns, and specification optimization and sanity checking. Salty interfaces with the separately developed synthesis tool Slugs to produce a system or controller design, and Salty translates this design to a software implementation in a variety of languages. We demonstrate Salty on an application involving coordination of multiple unmanned air vehicles (UAVs) and provide a workflow for connecting synthesized UAV controllers to freely available UAV planning and simulation software suites UxAS and AMASE.

We present a new framework for motion planning that wraps around existing kinodynamic planners and guarantees recursive feasibility when operating in a priori unknown, static environments. Our approach makes strong guarantees about overall safety and collision avoidance by utilizing a robust controller derived from reachability analysis. We ensure that motion plans never exit the safe backward reachable set of the initial state, while safely exploring the space. This preserves the safety of the initial state, and guarantees that that we will eventually find the goal if it is possible to do so while exploring safely. We implement our framework in the Robot Operating System (ROS) software environment and demonstrate it in a real-time simulation.

A laparoscope is a key element in Minimally Invasive Surgery (MIS) as it provides visual feedback to the surgeon. To overcome the drawbacks induced by its manual operation by a human assistant, it can be fixed on the end-effector of a robotic assistant teleoperated by the surgeon: laparoscope displacements are commanded through a master input interface (e.g., joysticks, voice control, etc.) and replicated accordingly at the slave level. In this approach, precision is of high importance to ensure a good operability by the surgeon. This is why the state-of-the-art relies on rigid laparoscope holders with high-gain PID position control, ensuring high static and dynamic precision. However, in the event of undetected obstacles, such stiff systems generate high forces that may cause harm to the patient. Rather, a compliant behaviour is desirable but it leads to a lack of precision when disturbances occur, such as the unknown friction between the trocar and the laparoscope. In this paper we present a “compliant-and-precise” laparo-scope holder with 4 active Degrees of Freedom (DoFs). Its design is based on cable transmission used for haptic interfaces, thus it exhibits very high backdrivability. The paper shows how an intelligent PID position controller can be used to compensate for unknown friction at the trocar while keeping very low PID gains and a satisfactory tracking precision.

The paper proposes a path planning algorithm for cluttered environment and maze. The proposed planning algorithm exploits the merit of convex optimization while forming the convex navigable free-spaces, ensuring safety of the vehicle. The contiguous convex free-spaces are iteratively computed from a random-walk based seed generation method to create a contiguous navigable geometry. Inside this contiguous navigable geometry an undirected graph is then created, whose each node and edge belong to at least one convex region which boils down the path planning problem into a graph search problem. In addition, the proposed multiple query planning algorithm can merge the user provided feasible initial and goal configuration with the existing undirected graph in each plan, without deteriorating the planning performance in terms of run-time and path length. Simulation and experimental results confirm the superiority of the proposed planning algorithm jointly in terms of both path length and run-time by a significant margin.

In this work, we propose an algorithm that can plan safe and efficient robot trajectories in real time, given time-parameterized motion predictions, in order to avoid fast-moving obstacles in human-robot collaborative environments. Our algorithm is able to reduce the robot configuration space and the time domain significantly by constructing a Lazy Safe Interval Probabilistic Roadmap based on a pre-planned path. The algorithm then plans efficient obstacle-avoidance strategies within the space-time roadmap. We benchmarked our algorithm by evaluating the performance of a simulated 6-joint manipulator attempting to avoid a quickly moving human hand, using a dataset collected from human experiments. We compared our algorithm's performance with those of 8 variations of prior state-of-the-art planners. Results from this empirical evaluation indicate that our method generated safe plans in 97.5% of the evaluated situations, achieved a planning speed 30 times faster than the benchmarked methods that planned in the time domain without space reduction, and accomplished the minimal solution execution time among the benchmarked planners with a similar planning speed.

Many current autonomous systems are being designed with a strong reliance on black box predictions from deep neural networks (DNNs). However, DNNs tend to be overconfident in predictions on unseen data and can give unpredictable results for far-from-distribution test data. The importance of predictions that are robust to this distributional shift is evident for safety-critical applications, such as collision avoidance around pedestrians. Measures of model uncertainty can be used to identify unseen data, but the state-of-the-art extraction methods such as Bayesian neural networks are mostly intractable to compute. This paper uses MC-Dropout and Bootstrapping to give computationally tractable and parallelizable uncertainty estimates. The methods are embedded in a Safe Reinforcement Learning framework to form uncertainty-aware navigation around pedestrians. The result is a collision avoidance policy that knows what it does not know and cautiously avoids pedestrians that exhibit unseen behavior. The policy is demonstrated in simulation to be more robust to novel observations and take safer actions than an uncertainty-unaware baseline.

Human-robot collaboration in industrial settings calls for implementing safety measures to ensure there is no risk to humans working in such an environment. In human-robot physical collaboration, an object or a load is handled by both human and the robot. Developing a safety framework for the robot is a requirement for preventing collisions during performing a task. In this paper, force myography (FMG) data are used to develop a control scheme for the robot such that it can work with the human worker while avoiding collisions. Force myography quantifies the activities of human muscles when applying forces to handle an object. A neural network-based approach is then used to select the most informative features of the FMG signal. The developed control scheme incorporates the FMG data and the robot dynamics to obtain a prediction about the next step of the cooperation task and to plan the robot motion accordingly. The proposed approach is evaluated experimentally in real time in a moving objects task which requires appropriate complementary actions from the robot and the human user. The results of this study show that the proposed scheme can successfully plan the robot motion based on the actions of the human user.

Complex robot motions are frequently generated by composing simpler primitive movements. We use this approach to formulate robot motion plans as sequences of primitives to be executed one after the other. When dealing with dynamical movement primitives, besides accomplishing the high-level objective, planners must also reason about the effect of the plan's execution on the safety of the platform. This task is exacerbated by the presence of disturbances, such as non-vanishing external forces. To address this issue, we present a framework that builds on rigorous control-theoretic tools to generate safely executable motion plans for externally excited robotic systems. We illustrate the proposed framework on adapting the motion of a 3D bipedal robot model to persistent external forcing by switching among dynamic movement primitives, each corresponding to a limit-cycle walking gait.

We propose a linear MPC scheme for online computation of reactive walking motions, necessary for fast interactions such as physical collaboration with humans or collision avoidance in crowds. Unlike other existing schemes, it provides fully adaptable height, adaptable step placement and complete kinematic and dynamic feasibility guarantees, making it possible to walk perfectly safely on a piecewise horizontal ground such as stairs. A linear formulation is proposed, based on efficiently bounding the nonlinear term introduced by vertical motion, considering two linear constraints instead of one nonlinear constraint. Balance and Passive Safety guarantees are secured by enforcing a 3D capturability constraint. Based on a comparison between CoM and CoP trajectories involving exponentials instead of polynomials, this capturability constraint involves a CoM motion stopping along a segment of line, always maintaining complete kinematic and dynamic feasibility.

We present a discrete-optimization technique for finding feasible robot arm trajectories that pass through provided 6-DOF Cartesian-space end-effector paths with high accuracy, a problem called pathwise-inverse kinematics. The output from our method consists of a path function of joint-angles that best follows the provided end-effector path function, given some definition of “best”. Our method, called Stampede, casts the robot motion translation problem as a discrete-space graph-search problem where the nodes in the graph are individually solved for using non-linear optimization; framing the problem in such a way gives rise to a well-structured graph that affords an effective best path calculation using an efficient dynamic-programming algorithm. We present techniques for sampling configuration space, such as diversity sampling and adaptive sampling, to construct the search-space in the graph. Through an evaluation, we show that our approach performs well in finding smooth, feasible, collision-free robot motions that match the input end-effector trace with very high accuracy, while alternative approaches, such as a state-of-the-art per-frame inverse kinematics solver and a global non-linear trajectory-optimization approach, performed unfavorably.

This paper combines techniques from Formal Methods and Human-Robot Interaction (HRI) to address the challenge of a robot walking with a human while maintaining a socially acceptable distance and avoiding collisions. We formulate a set of constraints on the robot motion using Satisfiability Modulo Theories (SMT) formulas, and synthesize robot control that is guaranteed to be safe and correct. Due to its use of high-level formal specifications, the controller is able to provide feedback to the user in situations where human behavior causes the robot to fail. This feedback allows the human to adjust their behavior and recover joint navigation. We demonstrate the behavior of the robot in a variety of simulated scenarios and compare it to utility-based side-by-side navigation control.

As the SLAM research area matures and the number of SLAM systems available increases, the need for frameworks that can objectively evaluate them against prior work grows. This new version of SLAMBench moves beyond traditional visual SLAM, and provides new support for scene understanding and non-rigid environments (dynamic SLAM). More concretely for dynamic SLAM, SLAMBench 3.0 includes the first publicly available implementation of DynamicFusion, along with an evaluation infrastructure. In addition, we include two SLAM systems (one dense, one sparse) augmented with convolutional neural networks for scene understanding, together with datasets and appropriate metrics. Through a series of use-cases, we demonstrate the newly incorporated algorithms, visulation aids and metrics (6 new metrics, 4 new datasets and 5 new algorithms).

This paper proposes a SEG-VoxelNet that takes RGB images and LiDAR point clouds as inputs for accurately detecting 3D vehicles in autonomous driving scenarios, which for the first time introduces semantic segmentation technique to assist the 3D LiDAR point cloud based detection. Specifically, SEG-VoxelNet is composed of two sub-networks: an image semantic segmentation network (SEG-Net) and an improved-VoxelNet. The SEG-Net generates the semantic segmentation map which represents the probability of the category for each pixel. The improved-VoxelNet is capable of effectively fusing point cloud data with image semantic feature and generating accurate 3D bounding boxes of vehicles. Experiments on the KITTI 3D vehicle detection benchmark show that our approach outperforms the methods of state-of-the-art.

Scaling up the software system on service robots increases the maintenance burden of developers and the risk of resource contention of the computer embedded on robots. As a result, developers spend much time on configuring, deploying, and monitoring the robot software system; robots may utilize significant computer resources when all software processes are running. We present Rorg, a Linux container-based scheme to manage, schedule, and monitor software components on service robots. Although Linux containers are already widely-used in cloud environments, this technique is challenging to efficiently adopt in service robot systems due to multi-tasking, resource constraints and performance requirements. To pave the way of Linux containers on service robots in an efficient manner, we present a programmable container management interface and a resource time-sharing mechanism incorporated with the Robot Operating System (ROS). Rorg allows developers to pack software into self-contained images and runs them in isolated environments using Linux containers; it also allows the robot to turn on and off software components on demand to avoid resource contention. We evaluate Rorg with a long-term autonomous tour guide robot: It manages 41 software components on the robot and relieved our maintenance burden, and it also reduces CPU load by 45.5% and memory usage by 16.5% on average.

Deep learning provides a powerful tool for robotic perception in the open world. However, real-world robotic systems, especially mobile robots, must be able to react intelligently and safely even in unexpected circumstances. This requires a system that knows what it knows, and can estimate its own uncertainty for unfamiliar, out-of-distribution observations. Approximate Bayesian approaches are commonly used to estimate uncertainty for neural network predictions, but struggle with out-of-distribution observations. Generative models can in principle detect out-of-distribution observations as those with a low estimated density, but overly pessimistic as an uncertainty measure, since the mere presence of an out-of-distribution input does not by itself indicate an unsafe situation. Intuitively, we would like a perception system that can detect when task-salient parts of the image are unfamiliar or uncertain, while ignoring task-irrelevant features. In this paper, we present a method for uncertainty-aware robotic perception that combines generative modeling and model uncertainty. Our method estimates an uncertainty measure about the model's prediction, taking into account an explicit generative model of the observation distribution to handle out-of-distribution inputs. We evaluate our method on an action-conditioned collision prediction task with both simulated and real data, and demonstrate that our approach improves on a variety of Bayesian neural network techniques.

Grasping objects in a cluttered environment is challenging due to the lack of collision free grasp affordances. In such conditions, the target object touches or is covered by other objects in the scene, resulting in a failed grasp. To address this problem, we propose a strategy of singulating the object from its surrounding clutter, which consists of previously unseen objects, by means of lateral pushing movements. We employ reinforcement learning for obtaining optimal push policies given depth observations of the scene. The action-value function(Q-function) is approximated with a deep neural network. We train the robot in simulation and we demonstrate that the transfer of learned policies to the real environment is robust.

When registering 3-D point clouds it is expected that some points in one cloud do not have corresponding points in the other cloud. These non-correspondences are likely to occur near one another, as surface regions visible from one sensor pose are obscured or out of frame for another. In this work, a hidden Markov random field model is used to capture this prior within the framework of the iterative closest point algorithm. The EM algorithm is used to estimate the distribution parameters and learn the hidden component memberships. Experiments are presented demonstrating that this method outperforms several other outlier rejection methods when the point clouds have low or moderate overlap.

This paper presents the robust Adaptive unscented Kalman filter (RAUKF) for attitude estimation. Since the proposed algorithm represents attitude as a unit quaternion, all basic tools used, including the standard UKF, are adapted to the unit quaternion algebra. Additionally, the algorithm adopts an outlier detector algorithm to identify abrupt changes in the UKF innovation and an adaptive strategy based on covariance matching to tune the measurement covariance matrix online. Adaptation and outlier detection make the proposed algorithm robust to fast and slow perturbations such as magnetic field interference and linear accelerations. Experimental results with a manipulator robot suggest that our method overcomes other algorithms found in the literature.