IROS 2018 论文列表

This work presents Semi-Supervised SLAM - a method for developing a map suitable for coarse localization within an underground environment with minimal human intervention, with system characteristics driven by real-world requirements of major mining companies. This work leverages existing information common within a mining environment - namely a surveyed mine map - which is used to sparsely ground map locations within the mine environment, increasing map accuracy and allowing localization within a global frame. Map creation utilizes a low cost camera sensor and minimal user information to produce a map which can be used for single camera localization within a mining environment. We evaluate the localization capabilities of the proposed approach in depth by performing data collection on operational underground mining vehicles within an active underground mine and by simulating occlusions common to the environment such as dust and water. The proposed system is capable of producing maps which have an average localization error 2.5 times smaller than the next best performing method ORB-SLAM2, comparable localization performance to a state-of-the-art deep learning approach (which is not a feasible solution due to both compute and training requirements) and is robust to simulated environmental obscurants.

An understanding of the nature of objects could help robots to solve both high-level abstract tasks and improve performance at lower-level concrete tasks. Although deep learning has facilitated progress in image understanding, a robot's performance in problems like object recognition often depends on the angle from which the object is observed. Traditionally, robot sorting tasks rely on a fixed top-down view of an object. By changing its viewing angle, a robot can select a more semantically informative view leading to better performance for object recognition. In this paper, we introduce the problem of semantic view selection, which seeks to find good camera poses to gain semantic knowledge about an observed object. We propose a conceptual formulation of the problem, together with a solvable relaxation based on clustering. We then present a new image dataset consisting of around 10k images representing various views of 144 objects under different poses. Finally we use this dataset to propose a first solution to the problem by training a neural network to predict a “semantic score” from a top view image and camera pose. The views predicted to have higher scores are then shown to provide better clustering results than fixed top-down views.

Semantic segmentation is a challenging problem that can benefit numerous robotics applications, since it provides information about the content at every image pixel. Solutions to this problem have recently witnessed a boost on performance and results thanks to deep learning approaches. Unfortunately, common deep learning models for semantic segmentation present several challenges which hinder real life applicability in many domains. A significant challenge is the need of pixel level labeling on large amounts of training images to be able to train those models, which implies a very high cost. This work proposes and validates a simple but effective approach to train dense semantic segmentation models from sparsely labeled data. Labeling only a few pixels per image reduces the human interaction required. We find many available datasets, e.g., environment monitoring data, that provide this kind of sparse labeling. Our approach is based on augmenting the sparse annotation to a dense one with the proposed adaptive superpixel segmentation propagation. We show that this label augmentation enables effective learning of state-of-the-art segmentation models, getting similar results to those models trained with dense ground-truth. We demonstrate the applicability of the presented approach to different image modalities in real domains (underwater, aerial and urban scenarios) with publicly available datasets.

Recent advances in monocular SLAM have enabled real-time capable systems which run robustly under the assumption of a static environment, but fail in presence of dynamic scene changes and motion, since they lack an explicit dynamic outlier handling. We propose a semantic monocular SLAM framework designed to deal with highly dynamic environments, combining feature-based and direct approaches to achieve robustness under challenging conditions. The proposed approach exploits semantic information extracted from the scene within an explicit probabilistic model, which maximizes the probability for both tracking and mapping to rely on those scene parts that do not present a relative motion with respect to the camera. We show more stable pose estimation in dynamic environments and comparable performance to the state of the art on static sequences on the Virtual KITTI and Synthia datasets.

We present a filtering-based method for semantic mapping to simultaneously detect objects and localize their 6 degree-of-freedom pose. For our method, called Contextual Temporal Mapping (or CT-Map), we represent the semantic map as a belief over object classes and poses across an observed scene. Inference for the semantic mapping problem is then modeled in the form of a Conditional Random Field (CRF). CT-Map is a CRF that considers two forms of relationship potentials to account for contextual relations between objects and temporal consistency of object poses, as well as a measurement potential on observations. A particle filtering algorithm is then proposed to perform inference in the CT-Map model. We demonstrate the efficacy of the CT-Map method with a Michigan Progress Fetch robot equipped with a RGB-D sensor. Our results demonstrate that the particle filtering based inference of CT-Map provides improved object detection and pose estimation with respect to baseline methods that treat observations as independent samples of a scene.

In an autonomous vehicle setting, we propose a method for the estimation of a semantic grid, i.e. a bird's eye grid centered on the car's position and aligned with its driving direction, which contains high-level semantic information about the environment and its actors. Each grid cell contains a semantic label with divers classes, as for instance {Road, Vegetation, Building, Pedestrian, Car...}. We propose a hybrid approach, which combines the advantages of two different methodologies: we use Deep Learning to perform semantic segmentation on monocular RGB images with supervised learning from labeled groundtruth data. We combine these segmentations with occupancy grids calculated from LIDAR data using a generative Bayesian particle filter. The fusion itself is carried out with a deep neural network, which learns to integrate geometric information from the LIDAR with semantic information from the RGB data. We tested our method on two datasets, namely the KITTI dataset, which is publicly available and widely used, and our own dataset obtained with our own platform, equipped with a LIDAR and various sensors. We largely outperform baselines which calculate the semantic grid either from the RGB image alone or from LIDAR output alone, showing the interest of this hybrid approach.

We propose a new approach for generating training data for the task of drivable area segmentation with deep neural networks (DNN). The impressive progress of deep learning in recent years demonstrated a superior performance of DNNs over traditional machine learning and deterministic algorithms for various tasks. Nevertheless, the acquisition of large-scale datasets with associated ground truth labels still poses an expensive and labor-intensive problem. We contribute to the solution of this problem for the task of road segmentation by proposing an automatic labeling pipeline which leverages a deterministic stereo-based approach for ground plane detection to create large datasets suitable for training neural networks. Based on the popular Cityscapes [1] and KITTI dataset [2] and two off-the-shelf DNNs for semantic segmentation, we show that we can achieve good segmentation results on monocular images, which substantially exceed the performance of the algorithm employed for automatic labeling without the need of any manual annotation.

Formation control strategies are fundamentally impacted by the sensing modalities present in the multi-robot team. Infinitesimal shape-similarity describes frameworks for which maintaining the relative angles between robots in formation also maintains the shape up to translation, rotation, and uniform scaling; however, ensuring invariance of the formation to these motions requires that the robots measure a sufficient number of angles, which means that the topology of the frame-work must be carefully designed. In this paper, we investigate the self-assembly of a class of infinitesimally shape-similar frameworks by robots equipped with bearing-only sensors. To accomplish self-assembly, we introduce a rank condition on the shape-similarity matrix for analyzing frameworks; we then use this rank condition to show that triangulations are infinitesimally shape-similar. A graph grammar is presented to assemble triangulations, and a controller is designed to achieve self-assembly of a team of differential-drive robots.

This paper proposes an approach for segmenting a task consisting of compliant motions into phases, learning a primitive for each segmented phase of the task, and reproducing the task by sequencing primitives online based on the learned model. As compliant motions can “probe” the environment, using the interaction between the robot and the environment to detect phase transitions can make the transitions less prone to positional errors. This intuition leads us to model a task with a non-homogeneous Hidden Markov Model (HMM), wherein hidden phase transition probabilities depend on the interaction with the environment (wrench measured by an F/T sensor). Expectation-maximization algorithm is employed in estimating the parameters of the HMM model. During reproduction, the phase changes of a task are detected online using the forward algorithm, with the parameters learned from demonstrations. Cartesian impedance controller parameters are learned from the demonstrations to reproduce each phase of the task. The proposed approach is studied with a KUKA LWR4+ arm in two setups. Experiments show that the method can successfully segment and reproduce a task consisting of compliant motions with one or more demonstrations, even when demonstrations do not have the same starting position and external forces occur from different directions. Finally, we demonstrate that the method can also handle rotational motions.

In this work we introduce Natural Segmentation and Matching (NSM), an algorithm for reliable localization, using laser, in both urban and natural environments. Current state-of-the-art global approaches do not generalize well to structure-poor vegetated areas such as forests or orchards. In these environments clutter and perceptual aliasing prevents repeatable extraction of distinctive landmarks between different test runs. In natural forests, tree trunks are not distinctive, foliage intertwines and there is a complete lack of planar structure. In this paper we propose a method for place recognition which uses a more involved feature extraction process which is better suited to this type of environment. First, a feature extraction module segments stable and reliable object-sized segments from a point cloud despite the presence of heavy clutter or tree foliage. Second, repeatable oriented key poses are extracted and matched with a reliable shape descriptor using a Random Forest to estimate the current sensor's position within the target map. We present qualitative and quantitative evaluation on three datasets from different environments - the KITTI benchmark, a parkland scene and a foliage-heavy forest. The experiments show how our approach can achieve place recognition in woodlands while also outperforming current state-of-the-art approaches in urban scenarios without specific tuning.

Symmetry is a common property shared by the majority of man-made objects. This paper presents a novel bottom-up approach for segmenting symmetric objects and recovering their symmetries from 3D pointclouds of natural scenes. Candidate rotational and reflectional symmetries are detected by fitting symmetry axes/planes to the geometry of the smooth surfaces extracted from the scene. Individual symmetries are used as constraints for the foreground segmentation problem that uses symmetry as a global grouping principle. Evaluation on a challenging dataset shows that our approach can reliably segment objects and extract their symmetries from incomplete 3D reconstructions of highly cluttered scenes, outperforming state-of-the-art methods by a wide margin.

As modern robots become more intelligent, also their use will broaden in public and professional areas. While the aim is to make robots beneficial to humans and society, using those complex machines in complex environments will eventually lead to incidents. To enable forensic investigations, ethical evaluations and transparent function of intelligent robots in a society, we contribute the concept of a secure robot data recorder that is similar to a flight data recorder in airplanes. However, since robots work in a highly networked and uncontrolled environment, our concept pays special attention to security and tamper proofness. In addition, we extend the concept with an approach inspired by cockroaches to increase the functional integrity of the robot. We present a prototype implementation along with discussions on the required properties and limits of secure data recording.

This paper presents a framework for fast and robust motion planning designed to facilitate automated driving. The framework allows for real-time computation even for horizons of several hundred meters and thus enabling automated driving in urban conditions. This is achieved through several features. Firstly, a convenient geometrical representation of both the search space and driving constraints enables the use of classical path planning approach. Thus, a wide variety of constraints can be tackled simultaneously (other vehicles, traffic lights, etc.). Secondly, an exact cost-to-go map, obtained by solving a relaxed problem, is then used by A*-based algorithm with model predictive flavour in order to compute the optimal motion trajectory. The algorithm takes into account both distance and time horizons. The approach is validated within a simulation study with realistic traffic scenarios. We demonstrate the capability of the algorithm to devise plans both in fast and slow driving conditions, even when full stop is required.

Scan similarity-based pose graph construction method for graph SLAM is proposed. To perform delicate pose graph SLAM, front-end that constructs a graph as well as back-end that optimizes the constructed graph is an important task. Generally, there is an error accumulation phenomenon during the odometry estimation process. This paper focuses on the method of creating a high quality graph by suggesting ways to improve the graph accuracy since the accumulated errors in the graph might degrade the performance of the entire graph SLAM. We deal with one of our previous works, dynamic keyframe selection technique, based on scan similarity computation method more precisely and suggest a loop closure detection method by exploiting previously proposed 2-D laser scan descriptor. To verify objective performance of the proposed method, the experimental results of the odometry estimation are shown by using the benchmark dataset and the real world dataset. Additionally, results of the pose graph SLAM are shown for the real world dataset which include the loop clorues.

Compared to diverse feature detectors and descriptors used for visual scenes, describing a place using structural information is relatively less reported. Recent advances in simultaneous localization and mapping (SLAM) provides dense 3D maps of the environment and the localization is proposed by diverse sensors. Toward the global localization based on the structural information, we propose Scan Context, a non-histogram-based global descriptor from 3D Light Detection and Ranging (LiDAR) scans. Unlike previously reported methods, the proposed approach directly records a 3D structure of a visible space from a sensor and does not rely on a histogram or on prior training. In addition, this approach proposes the use of a similarity score to calculate the distance between two scan contexts and also a two-phase search algorithm to efficiently detect a loop. Scan context and its search algorithm make loop-detection invariant to LiDAR viewpoint changes so that loops can be detected in places such as reverse revisit and corner. Scan context performance has been evaluated via various benchmark datasets of 3D LiDAR scans, and the proposed method shows a sufficiently improved performance.

Visual localization under large changes in scale is an important capability in many robotic mapping applications, such as localizing at low altitudes in maps built at high altitudes, or performing loop closure over long distances. Existing approaches, however, are robust only up to about a 3× difference in scale between map and query images. We propose a novel combination of deep-learning-based object features and state-of-the-art SIFT point-features that yields improved robustness to scale change. This technique is training-free and class-agnostic, and in principle can be deployed in any environment out-of-the-box. We evaluate the proposed technique on the KITTI Odometry benchmark and on a novel dataset of outdoor images exhibiting changes in visual scale of 7× and greater, which we have released to the public. Our technique consistently outperforms localization using either SIFT features or the proposed object features alone, achieving both greater accuracy and much lower failure rates under large changes in scale.

The inherent scale ambiguity in monocular vision is a well known issue that forces the integration of other sensory sources to obtain metric references. However, 2D or 3D LiDARs and RGB-D sensors, while guaranteeing metrological accuracy, impose a non negligible burden both in terms of computational load and power requirements limiting the feasibility of being implemented on small exploration vehicles. This paper presents a scale aware monocular Visual Odometry framework that fuses range data from a laser altimeter in order to recover and maintain a correct metric scale. The proposed Visual Odometry method consists of a keyframe based tracking and mapping algorithm using optical flow where range data serves as a scale constraint on a keyframe to keyframe basis. An optimization backend based on iSAM2 is employed in order to refine the trajectory and map estimates eliminating the scale drift without the need of performing loop closures. We demonstrate that our algorithm can obtain very similar performances to state of the art stereo visual SLAM and RGB-D methods.

In this paper, we introduce a Markov chain Monte Carlo (MCMC)method to solve multi-objective motion-planning problems. We formulate the problem of finding Pareto-optimal trajectories as a problem of sampling trajectories from a Pareto-optimal set. We define an implicit uniform distribution over the Pareto-frontier using a dominance function and then sample in the space of trajectories. The nature of MCMC guarantees the convergence to the Pareto-frontier, while the uniform distribution ensures the diversity of the trajectories. We also propose progressive objective evaluation to increase efficiency in problems with expensive-to-evaluate objective functions. This enables determination of dominance relationship between trajectories before they are entirely evaluated. We finally analyze the effectiveness of the framework and its applications in robotics.

In this paper we present a framework that allows the motion control of a robotic arm automatically handling different kinds of safety-related tasks. The developed controller is based on a Task-Priority Inverse Kinematics algorithm that allows the manipulator's motion while respecting constraints defined either in the joint or in the operational space in the form of equality-based or set-based tasks. This gives the possibility to define, among the others, tasks as joint-limits, obstacle avoidance or limiting the workspace in the operational space. Additionally, an algorithm for the real-time computation of the minimum distance between the manipulator and other objects in the environment using depth measurements has been implemented, effectively allowing obstacle avoidance tasks. Experiments with a Jaco2 manipulator, operating in an environment where an RGB-D sensor is used for the obstacles detection, show the effectiveness of the developed system.