IROS 2016 论文列表

Scene understanding is an important prerequisite for vehicles and robots that operate autonomously in dynamic urban street scenes. For navigation and high-level behavior planning, the robots not only require a persistent 3D model of the static surroundings—equally important, they need to perceive and keep track of dynamic objects. In this paper, we propose a method that incrementally fuses stereo frame observations into temporally consistent semantic 3D maps. In contrast to previous work, our approach uses scene flow to propagate dynamic objects within the map. Our method provides a persistent 3D occupancy as well as semantic belief on static as well as moving objects. This allows for advanced reasoning on objects despite noisy single-frame observations and occlusions. We develop a novel approach to discover object instances based on the temporally consistent shape, appearance, motion, and semantic cues in our maps. We evaluate our approaches to dynamic semantic mapping and object discovery on the popular KITTI benchmark and demonstrate improved results compared to single-frame methods.

The view planning problem is the problem that involves finding suitable viewpoints for vision-related tasks such as inspection or reconstruction. In this paper, we propose a novel view planning algorithm for a camera-equipped Unmanned Aerial Vehicle (UAV) acquiring visual geometric information of target objects in its surrounding environment. The proposed model-based approach makes use of iterative random sampling and a probabilistic potential-field method to generate candidate viewpoints in a non-deterministic manner. Combinatorial optimization is then applied to select the most suitable subset of these candidate viewpoints to complete the given visual inspection or shape reconstruction task. The effectiveness of the proposed method is demonstrated through a number of computational tests that compare its overall performance against two previous methods. A field-test is also performed to demonstrate the method's applicability in a real world UAV-based shape reconstruction task of an outdoor statue.

We present SaDDP, a sampled version of the widely used differential dynamic programming (DDP) control algorithm. We contribute through establishing a novel connection between two major branches of robotics control research, that is, gradient-based methods such as DDP, and Monte Carlo methods such as path integral control (PI) that utilize random simulated trajectory rollouts. One of our key observations is that the Taylor-expansion, central to DDP, can be reformulated in terms of second-order statistics computed of the sampled trajectories. SaDDP makes few assumptions about the controlled system and works with black-box dynamics simulations with non-smooth contacts. Our simulation results show that the method outperforms PI and CMA-ES in both a simple linear-quadratic problem, and a multilink arm reaching task with obstacles.

This paper presents a novel approach for safeguarding a mobile manipulator. To overcome the shortcomings of state-of-the-art safeguarding techniques, we present a dynamic approach capable of covering different situations and adapting itself to the situation at hand. The proposed approach is based on the continuous dynamic update of a safety field using both exteroceptive and proprioceptive data. The proprioceptive data are the platform velocity vector and the manipulator position; the exteroceptive data refers to the environment in which the mobile manipulator is moving, namely distances to obstacles acquired by laser scanners. The effectiveness of the proposed approach has been validated in an industrial test case scenario in which the robot had to execute a fetch and carry task while safely coexisting with human workers. Experimental results proved that the use of dynamic protection fields allowed the robot to carry out its tasks with a significant reduction (about 50%) of the execution time.

In this work, we consider the labeled multi-robot planning problem. In this paradigm, a team of robots at fixed start positions must navigate to pre-specified and noninterchangable goal positions. While many algorithms have been proposed for finding optimal solutions to this problem, most methods assume that the robots are kinematic agents, whereas in reality, robots often have high-order dynamics that must be respected by their trajectories. Here, we propose a centralized method for generating trajectories for teams of robots with general nth-order dynamics navigating to labeled goals. Our algorithm is safe and complete and additionally allows for decoupled optimization of each robot's trajectory as a Quadratic Program with linear constraints. We present simulation results for teams of up to 20 robots.

Throughout the wide range of aerial robot related applications, selecting a particular airframe is often a trade-off. Fixed-wing small-scale unmanned aerial vehicles (UAVs) typically have difficulty surveying at low altitudes while quadrotor UAVs, having more maneuverability, suffer from limited flight time. Recent prior work [1] proposes a solar-powered small-scale aerial vehicle designed to transform between fixed-wing and quad-rotor configurations. Surplus energy collected and stored while in a fixed-wing configuration is utilized while in a quad-rotor configuration. This paper presents an improvement to the robot's design in [1] by pursuing a modular airframe, an optimization of the hybrid propulsion system, and solar power electronics. Two prototypes of the robot have been fabricated for independent testing of the airframe in fixed-wing and quad-rotor states. Validation of the solar power electronics and hybrid propulsion system designs were demonstrated through a combination of simulation and empirical data from prototype hardware.

Mapping and self-localization in unknown environments are fundamental capabilities in many robotic applications. These tasks typically involve the identification of objects as unique features or landmarks, which requires the objects both to be detected and then assigned a unique identifier that can be maintained when viewed from different perspectives and in different images. The data association and simultaneous localization and mapping (SLAM) problems are, individually, well-studied in the literature. But these two problems are inherently tightly coupled, and that has not been well-addressed. Without accurate SLAM, possible data associations are combinatorial and become intractable easily. Without accurate data association, the error of SLAM algorithms diverge easily. This paper proposes a novel nonparametric pose graph that models data association and SLAM in a single framework. An algorithm is further introduced to alternate between inferring data association and performing SLAM. Experimental results show that our approach has the new capability of associating object detections and localizing objects at the same time, leading to significantly better performance on both the data association and SLAM problems than achieved by considering only one and ignoring imperfections in the other.

Motion planning in stochastic dynamic uncertain environments is critical in several applications such as human interacting robots, autonomous vehicles and assistive robots. In order to address these complex applications, several methods have been developed. The most successful methods often predict future obstacle locations in order identify collision-free paths. Since prediction can be computationally expensive, offline computations are commonly used, and simplifications such as the inability to consider the dynamics of interacting obstacles or possible stochastic dynamics are often applied. Online methods can be preferable to simulate potential obstacle interactions, but recent methods have been restricted to Gaussian interaction processes and uncertainty. In this paper we present an online motion planning method, Runtime Stochastic Ensemble Simulation (Runtime SES) planning, an inexpensive method for predicting obstacle motion with generic stochastic dynamics while maintaining a high planning success rate despite the potential presence of obstacle position error. Runtime SES planning evaluates the likelihood of collision for any state-time coordinate around the robot by performing Monte Carlo simulations online. This prediction is used to construct a customized Rapidly Exploring Random Tree (RRT) in order to quickly identify paths that avoid obstacles while moving toward a goal. We demonstrate Runtime SES planning in problems that benefit from online predictions, environments with strongly-interacting obstacles with stochastic dynamics and positional error. Through experiments that explore the impact of various parametrizations, robot dynamics and obstacle interaction models, we show that real-time capable planning with a high success rate is achievable in several complex environments.

Mobile service robots have the potential to improve the efficiency of fruit production in orchards. One of the key tasks that such robots must perform is traversing the rows. Many of the past implementations of row following in orchards have been developed for rows where the trees appear like walls on both sides. Another orchard structure that is used is the pergola, where a sparse array of trunks and posts hold up a canopy, which resembles a ceiling. Navigation in pergola structured environments has received less attention. The variations in the pergola environment- including the presence of tall weeds, hanging branches, undulating terrain and varying geometry-make following the rows a challenging problem. This paper presents solutions for finding the row centreline in pergola structured environments, in the presence of real world variability. A 3D laser scanner is used to measure the positions of posts and trunks, amongst the other features in the pergola. From the extracted features, the mode gradient of nearest neighbours is used to find the row direction and hence the centreline. The practicality of the system is demonstrated by autonomously driving a mobile robot through over 5000 meters of a kiwifruit orchard with a pergola structure, using the row detection method. This method performs favourably compared to an existing method of row detection in kiwifruit orchards.

Having a team of robots to perform a task such as mapping is faster and more reliable than doing the same with a single robot, which can be crucial in scenarios such as search and rescue. We are developing a fully distributed framework for collaborative mapping with large robot swarms that is robust to abrupt departure of robots due to malfunctions or network problems. While several approaches to multi-robot mapping have been proposed, most of them either build a collection of local sub-maps, or rely on a central authority to merge maps built by individual robots. Our framework is unique in that it requires no central authority, yet allows robots to simultaneously contribute to a single global map, which is stored in a decentralized fashion. This greatly improves the scalability of our system with respect to number of robots. However, our approach requires systematic coordination among robots in order to make modifications to the map. Unannounced departure of the robots makes coordination challenging, and can potentially make the map inconsistent or result in loss of data. We borrow ideas from the domain of distributed computing to address those challenges. Further, we demonstrate the robustness of the proposed system by subjecting it to various conditions in which participating robots fail.

Two robust kinematic controllers for position trajectory tracking of a perturbed wheeled mobile robot are presented. We address a final objective of fixed-time pose-regulation, which means that the robot position and orientation must reach desired final values simultaneously in a user-defined time. To achieve that, we propose the robust tracking of adequate trajectories for position, which drives the robot to get a desired final orientation due to the nonholonomic motion constraint. Hence, the main contribution of the paper is a complete strategy to define adequate reference trajectories as well as robust controllers to track them in order to enforce the pose-regulation of a wheeled mobile robot in a desired time. Realistic simulations show the good performance of the proposed scheme even in the presence of strong disturbances.

This paper investigates sound source mapping in a real environment using a mobile robot. Our approach is based on audio ray tracing which integrates occupancy grids and sound source localization using a laser range finder and a microphone array. Previous audio ray tracing approaches rely on all observed rays and grids. As such observation errors caused by sound reflection, sound occlusion, wall occlusion, sounds at misdetected grids, etc. can significantly degrade the ability to locate sound sources in a map. A three-layered selective audio ray tracing mechanism is proposed in this work. The first layer conducts frame-based unreliable ray rejection (sensory rejection) considering sound reflection and wall occlusion. The second layer introduces triangulation and audio tracing to detect falsely detected sound sources, rejecting audio rays associated to these misdetected sounds sources (short-term rejection). A third layer is tasked with rejecting rays using the whole history (long-term rejection) to disambiguate sound occlusion. Experimental results under various situations are presented, which proves the effectiveness of our method.

Autonomous robots enjoy a wide popularity nowadays and have been applied in many applications, such as home security, entertainment, delivery, navigation and guidance. It is vital for robots to track objects accurately in real time in these applications, so it is necessary to focus on tracking algorithms to improve the robustness, speed and accuracy. In this paper, we propose a real-time robust object tracking algorithm based on a hierarchical ensemble framework which incorporates information including individual pixel features, local patches and holistic target models. The framework combines multiple ensemble models simultaneously instead of using a single ensemble model individually. A discriminative model which accounts for the matching degree of local patches is adopted via a bottom ensemble layer, and a generative model which exploits holistic templates is used to search for the object based on the middle ensemble layer as well as an adaptive Kalman filter. We test the proposed tracker on challenging benchmark image sequences. The experimental results demonstrate that the proposed tracker performs superiorly against several state-of-the-art algorithms, especially when the appearance changes dramatically and the occlusions occur.

Detecting moving objects in dynamic scenes from sequences of lidar scans is an important task in object tracking, mapping, localization, and navigation. Many works focus on changes detection in previously observed scenes, while a very limited amount of literature addresses moving objects detection. The state-of-the-art method exploits Dempster-Shafer Theory to evaluate the occupancy of a lidar scan and to discriminate points belonging to the static scene from moving ones. In this paper we improve both speed and accuracy of this method by discretizing the occupancy representation, and by removing false positives through visual cues. Many false positives lying on the ground plane are also removed thanks to a novel ground plane removal algorithm. Efficiency is improved through an octree indexing strategy. Experimental evaluation against the KITTI public dataset shows the effectiveness of our approach, both qualitatively and quantitatively with respect to the state-of-the-art.

This paper presents a robust motion planning methodology for autonomous tracked vehicles navigating in a rough and unknown environment. Two fields of study are dealt with in this paper: motion planning and slip estimation. For the motion planner, the CC-RRT* algorithm is combined with LQG-MP. The motion planner uses a chance-constrained approach and considers the role of compensator in the planning step to provide a robust yet non-conservative planner. For the slip estimator, a stable yet practical online approach known as IPEM is used. IPEM compares the integrated prediction with the measurement to calculate appropriate parameters. The methodology performs online slip estimation and re-planning iteratively. This guarantees the safe travel of the vehicle even when there is an unexpected terrain change that can be fatal. The simulation result shows that the iterative estimation and re-planning plays a significant role in ensuring the safety of the vehicle.

To enable safe motion planning in a dynamic environment, it is vital to anticipate and predict object movements. In practice, however, an accurate object identification among multiple moving objects is extremely challenging, making it infeasible to accurately track and predict individual objects. Furthermore, even for a single object, its appearance can vary significantly due to external effects, such as occlusions, varying perspectives, or illumination changes. In this paper, we propose a novel recurrent network architecture called a recurrent flow network that can infer the velocity of each cell and the probability of future occupancy from a sequence of occupancy grids which we refer to as an occupancy flow. The parameters of the recurrent flow network are optimized using Bayesian optimization. The proposed method outperforms three baseline optical flow methods, Lucas-Kanade, Lucas-Kanade with Tikhonov regularization, and HornSchunck methods, and a Bayesian occupancy grid filter in terms of both prediction accuracy and robustness to noise.

Attaching a flexible tactile skin to an existing robotic system is relatively easy compared to integrating most other tactile sensor designs. In this paper we show that material classification purely based on the spatio-temporal signal of a flexible tactile skin can be robustly performed in a real world setting. We compare different classification algorithms and feature sets, including features adopted and extended from previous works in tactile material classification and that are based on the signal's Fourier spectrum. Our convolutional deep learning network architecture, which we also present here, is directly fed with the raw 24000 dimensional sensor signal and performs best by a large margin, reaching a classification accuracy of up to 97.3%.

Accurate and robust real-time map generation onboard of a fixed-wing UAV is essential for obstacle avoidance, path planning, and critical maneuvers such as autonomous take-off and landing. Due to the computational constraints, the required robustness and reliability, it remains a challenge to deploy a fixed-wing UAV with an online-capable, accurate and robust map generation framework. While photogrammetric approaches have underlying assumptions on the structure and the view of the camera, generic simultaneous localization and mapping (SLAM) approaches are computationally demanding. This paper presents a framework that uses the autopilot's state estimate as a prior for sliding window bundle adjustment and map generation. Our approach outputs an accurate geo-referenced dense point-cloud which was validated in simulation on a synthetic dataset and on two real-world scenarios based on ground control points.

Impedance control offers a theoretical basis for safe interaction between a robot and the environment, but model uncertainty, disturbances and actuation dynamics can compromise the accuracy of the rendered impedance in implementation. If both the interactive force and motion are directly sensed, the relationship between them can be robustly regulated to present the desired impedance dynamics. In this paper, a Disturbance Observer based controller architecture is presented which offers performance robustness for impedance control. Conditions for stability and passivity are developed, then this controller is analyzed on a series-elastic actuated system. The effect of actuation dynamics on both performance and stability is analyzed, then experimental results are presented.