ICRA 2019 论文列表

We present the design, fabrication, and feedforward control of a insect-sized (142 mg) aerial robot that is equipped with a bio-inspired inertial tail. A tail allows the robot to perform rapid inertial reorientation as well as to shift weight to modulate aerodynamic torques on its body. Here we present the first analysis of inertial reorientation using a piezo actuator, departing from previous work to date that has focused exclusively on actuation by DC electric motor. The primary difference is that unlike a geared motor system, the piezo-tail system operates as a resonant system, exhibiting slowly-decaying oscillations. We present a dynamic model of piezo-driven inertial reorientation, along with an open-loop feedforward controller that reduces excitation of the resonant mode. We validate our approach on a tethered testbed as well as a flight-capable prototype. Our results indicate that incorporating a tail can allow for more rapid dynamic maneuvers and could stabilize the robot during flight.

Radar detects stable, long-range objects under variable weather and lighting conditions, making it a reliable and versatile sensor well suited for ego-motion estimation. In this work, we propose a radar-only odometry pipeline that is highly robust to radar artifacts (e.g., speckle noise and false positives) and requires only one input parameter. We demonstrate its ability to adapt across diverse settings, from urban UK to off-road Iceland, achieving a scan matching accuracy of approximately 5.20 cm and 0.0929 deg when using GPS as ground truth (compared to visual odometry's 5.77 cm and 0.1032 deg). We present algorithms for key point extraction and data association, framing the latter as a graph matching optimization problem, and provide an in-depth system analysis.

State-of-the-art forward facing monocular visual-inertial odometry algorithms are often brittle in practice, especially whilst dealing with initialisation and motion in directions that render the state unobservable. In such cases having a reliable complementary odometry algorithm enables robust and resilient flight. Using the common local planarity assumption, we present a fast, dense, and direct frame-to-frame visual-inertial odometry algorithm for downward facing cameras that minimises a joint cost function involving a homography based photometric cost and an IMU regularisation term. Via extensive evaluation in a variety of scenarios we demonstrate superior performance than existing state-of-the-art downward facing odometry algorithms for Micro Aerial Vehicles (MAVs).

In this paper we propose a robust visual odometry system for a wide-baseline camera rig with wide field-of-view (FOV) fisheye lenses, which provides full omnidirectional stereo observations of the environment. For more robust and accurate ego-motion estimation we adds three components to the standard VO pipeline, 1) the hybrid projection model for improved feature matching, 2) multi-view P3P RANSAC algorithm for pose estimation, and 3) online update of rig extrinsic parameters. The hybrid projection model combines the perspective and cylindrical projection to maximize the overlap between views and minimize the image distortion that degrades feature matching performance. The multi-view P3P RANSAC algorithm extends the conventional P3P RANSAC to multi-view images so that all feature matches in all views are considered in the inlier counting for robust pose estimation. Finally the online extrinsic calibration is seamlessly integrated in the backend optimization framework so that the changes in camera poses due to shocks or vibrations can be corrected automatically. The proposed system is extensively evaluated with synthetic datasets with ground-truth and real sequences of highly dynamic environment, and its superior performance is demonstrated.

Simultaneous Localization and Mapping is a key requirement for many practical applications in robotics. In this work, we present RESLAM, a novel edge-based SLAM system for RGBD sensors. Due to their sparse representation, larger convergence basin and stability under illumination changes, edges are a promising alternative to feature-based or other direct approaches. We build a complete SLAM pipeline with camera pose estimation, sliding window optimization, loop closure and relocalisation capabilities that utilizes edges throughout all steps. In our system, we additionally refine the initial depth from the sensor, the camera poses and the camera intrinsics in a sliding window to increase accuracy. Further, we introduce an edge-based verification for loop closures that can also be applied for relocalisation. We evaluate RESLAM on wide variety of benchmark datasets that include difficult scenes and camera motions and also present qualitative results. We show that this novel edge-based SLAM system performs comparable to state-of-the-art methods, while running in real-time on a CPU. RESLAM is available as open-source software1.

Standardized evaluation measures have aided in the progress of machine learning approaches in disciplines such as computer vision and machine translation. In this paper, we make the case that robotic learning would also benefit from benchmarking, and present a template for a vision-based manipulation benchmark. Our benchmark is built on “REPLAB,” a reproducible and self-contained hardware stack (robot arm, camera, and workspace) that costs about 2000 USD and occupies a cuboid of size 70x40x60 cm. Each REPLAB cell may be assembled within a few hours. Through this low-cost, compact design, REPLAB aims to drive wide participation by lowering the barrier to entry into robotics and to enable easy scaling to many robots. We envision REPLAB as a framework for reproducible research across manipulation tasks, and as a step in this direction, we define a grasping benchmark consisting of a task definition, evaluation protocol, performance measures, and a dataset of over 50,000 grasp attempts. We implement, evaluate, and analyze several previously proposed grasping approaches to establish baselines for this benchmark. Project page with assembly instructions, additional details, and videos: https://goo.gl/5F9dP4.

In robotic surgery the motion of instruments and the laparoscopic camera is constrained by their insertion ports, i. e. a remote centre of motion (RCM). We propose a Simultaneous Localisation and Mapping (SLAM) approach that estimates laparoscopic camera motion under RCM constraints. To achieve this we derive a minimal solver for the absolute camera pose given two 2D-3D point correspondences (RCM-PnP) and also a bundle adjustment optimiser that refines camera poses within an RCM-constrained parameterisation. These two methods are used together with previous work on relative pose estimation under RCM [1] to assemble a SLAM pipeline suitable for robotic surgery. Our simulations show that RCM-PnP outperforms conventional PnP for a wide noise range in the RCM position. Results with video footage from a robotic prostatectomy show that RCM constraints significantly improve camera pose estimation.

Robots must cost less and be force-controlled to enable widespread, safe deployment in unconstrained human environments. We propose Quasi-Direct Drive actuation as a capable paradigm for robotic force-controlled manipulation in human environments at low-cost. Our prototype - Blue - is a human scale 7 Degree of Freedom arm with 2kg payload. Blue can cost less than $5000. We show that Blue has dynamic properties that meet or exceed the needs of human operators: the robot has a nominal position-control bandwidth of 7.5Hz and repeatability within 4mm. We demonstrate a Virtual Reality based interface that can be used as a method for telepresence and collecting robot training demonstrations. Manufacturability, scaling, and potential use-cases for the Blue system are also addressed. Videos and additional information can be found online at berkeleyopenarms.github.io.

Using the effects of quantum mechanics for computing challenges has been an often discussed topic for decades. The frequent successes and early products in this area, which we have seen in recent years, indicate that we are currently entering a new era of computing. This paradigm shift will also impact the work of robotic scientists and the applications of robotics. New possibilities as well as new approaches to known problems will enable the creation of even more powerful and intelligent robots that make use of quantum computing cloud services or co-processors. In this position paper, we discuss potential application areas and also point out open research topics in quantum computing for robotics. We go into detail on the impact of quantum computing in artificial intelligence and machine learning, sensing and perception, kinematics as well as system diagnosis. For each topic we point out where quantum computing could be applied based on results from current research.

We quantify the accuracy of various simulators compared to a real world robotic reaching and interaction task. Simulators are used in robotics to design solutions for real world hardware without the need for physical access. The `reality gap' prevents solutions developed or learnt in simulation from performing well, or at all, when transferred to real-world hardware. Making use of a Kinova robotic manipulator and a motion capture system, we record a ground truth enabling comparisons with various simulators, and present quantitative data for various manipulation-oriented robotic tasks. We show the relative strengths and weaknesses of numerous contemporary simulators, highlighting areas of significant discrepancy, and assisting researchers in the field in their selection of appropriate simulators for their use cases.

We present a system for interaction between co-located humans and mobile robots, which uses pointing gestures sensed by a wrist-mounted IMU. The operator begins by pointing, for a short time, at a moving robot. The system thus simultaneously determines: that the operator wants to interact; the robot they want to interact with; and the relative pose among the two. Then, the system can reconstruct pointed locations in the robot's own reference frame, and provide real-time feedback about them so that the user can adapt to misalignments. We discuss the challenges to be solved to implement such a system and propose practical solutions, including variants for fast flying robots and slow ground robots. We report different experiments with real robots and untrained users, validating the individual components and the system as a whole.

High-level human instructions often correspond to behaviors with multiple implicit steps. In order for robots to be useful in the real world, they must be able to to reason over both motions and intermediate goals implied by human instructions. In this work, we propose a framework for learning representations that convert from a natural-language command to a sequence of intermediate goals for execution on a robot. A key feature of this framework is prospection, training an agent not just to correctly execute the prescribed command, but to predict a horizon of consequences of an action before taking it. We demonstrate the fidelity of plans generated by our framework when interpreting real, crowd-sourced natural language commands for a robot in simulated scenes.

There has been an increasing interest in learning dynamics simulators for model-based control. Compared with off-the-shelf physics engines, a learnable simulator can quickly adapt to unseen objects, scenes, and tasks. However, existing models like interaction networks only work for fully observable systems; they also only consider pairwise interactions within a single time step, both restricting their use in practical systems. We introduce Propagation Networks (PropNet), a differentiable, learnable dynamics model that handles partially observable scenarios and enables instantaneous propagation of signals beyond pairwise interactions. With these innovations, our propagation networks not only outperform current learnable physics engines in forward simulation, but also achieves superior performance on various control tasks. Compared with existing deep reinforcement learning algorithms, model-based control with propagation networks is more accurate, efficient, and generalizable to novel, partially observable scenes and tasks.

Project AutoVision aims to develop localization and 3D scene perception capabilities for a self-driving vehicle. Such capabilities will enable autonomous navigation in urban and rural environments, in day and night, and with cameras as the only exteroceptive sensors. The sensor suite employs many cameras for both 360-degree coverage and accurate multi-view stereo; the use of low-cost cameras keeps the cost of this sensor suite to a minimum. In addition, the project seeks to extend the operating envelope to include GNSS-less conditions which are typical for environments with tall buildings, foliage, and tunnels. Emphasis is placed on leveraging multi-view geometry and deep learning to enable the vehicle to localize and perceive in 3D space. This paper presents an overview of the project, and describes the sensor suite and current progress in the areas of calibration, localization, and perception.

Radar presents a promising alternative to lidar and vision in autonomous vehicle applications, able to detect objects at long range under a variety of weather conditions. However, distinguishing between occupied and free space from raw radar power returns is challenging due to complex interactions between sensor noise and occlusion. To counter this we propose to learn an Inverse Sensor Model (ISM) converting a raw radar scan to a grid map of occupancy probabilities using a deep neural network. Our network is selfsupervised using partial occupancy labels generated by lidar, allowing a robot to learn about world occupancy from past experience without human supervision. We evaluate our approach on five hours of data recorded in a dynamic urban environment. By accounting for the scene context of each grid cell our model is able to successfully segment the world into occupied and free space, outperforming standard CFAR filtering approaches. Additionally by incorporating heteroscedastic uncertainty into our model formulation, we are able to quantify the variance in the uncertainty throughout the sensor observation. Through this mechanism we are able to successfully identify regions of space that are likely to be occluded.

We present a real-time dense mapping system which uses the predicted 2D semantic labels for optimizing the geometric quality of reconstruction. With a combination of Convolutional Neural Networks (CNNs) for 2D labeling and a Simultaneous Localization and Mapping (SLAM) system for camera trajectory estimation, recent approaches have succeeded in incrementally fusing and labeling 3D scenes. However, the geometric quality of the reconstruction can be further improved by incorporating such semantic prediction results, which is not sufficiently exploited by existing methods. In this paper, we propose to use semantic information to improve two crucial modules in the reconstruction pipeline, namely tracking and loop detection, for obtaining mutual benefits in geometric reconstruction and semantic recognition. Specifically for tracking, we use a novel probabilistic projective association approach to efficiently pick out candidate correspondences, where the confidence of these correspondences is quantified concerning similarities on all available short-term invariant features. For the loop detection, we incorporate these semantic labels into the original encoding through Randomized Ferns to generate a more comprehensive representation for retrieving candidate loop frames. Evaluations on a publicly available synthetic dataset have shown the effectiveness of our approach that considers such semantic hints as a reliable feature for achieving higher geometric quality.

This paper proposes a probabilistic approach for object search in clutter. Due to heavy occlusions, it is vital for an agent to be able to gradually reduce uncertainty in observations of the objects in its workspace by systematically rearranging them. Probabilistic methodologies present a promising sample-efficient alternative to handle the massively complex state-action space that inherently comes with this problem, avoiding the need for both exhaustive training samples and the accompanying heuristics for traversing a large-scale model during runtime. We approach the object search problem by extending a Gaussian Process active filtering strategy with an additional model for capturing state dynamics as the objects are moved over the course of the activity. This allows viable models to be built upon relatively scarce training data, while the complexity of the action space is also reduced by shifting objects over relatively short distances. Validation in both simulation and with a real Baxter robot with a limited number of training samples demonstrates the efficacy of the proposed approach.

Unmanned Aerial Vehicle (UAV) path planning algorithms often assume a knowledge reward function or priority map, indicating the most important areas to visit. In this paper we propose a method to create priority maps for monitoring or intervention of dynamic spreading processes such as wildfires. The presented optimization framework utilizes the properties of positive systems, in particular the separable structure of value (cost-to-go) functions, to provide scalable algorithms for surveillance and intervention. We present results obtained for a 16 and 1000 node example and convey how the priority map responds to changes in the dynamics of the system. The larger example of 1000 nodes, representing a fictional landscape, shows how the method can integrate bushfire spreading dynamics, landscape and wind conditions. Finally, we give an example of combining the proposed method with a travelling salesman problem for UAV path planning for wildfire intervention.

We investigate the role of geometric context in deep neural networks to establish better pedestrian detectors that are more robust to occlusions. Notwithstanding their demonstrated successes, deep object detectors under-perform in crowded scenes with high intra-category occlusions. One brute-force solution is to collect a large number of labeled training samples under occlusion, but the combinatorial increase in the labeling effort makes it an unaffordable solution. We argue that a promising and complementary direction to solve this problem is to bring geometric context to modulate feature learning in a DNN. We identify that an effective way to leverage geometric context is to induce it in two steps - through early fusion, by guiding region proposal generation to focus on occluded regions, and through late fusion, by penalizing misalignments of bounding boxes in both 2D and 3D. Our experiments on multiple state-of-the-art DNN detectors and detection benchmarks clearly demonstrates that our proposed method outperforms strong baselines by an average of 5%.