Head-mounted displays (HMDs) in room-scale virtual reality are usually tracked using inside-out visual SLAM algorithms. Alternatively, to track the motion of the HMD with respect to a fixed real-world reference frame, an outside-in instrumentation like a motion capture system can be adopted. However, outside-in tracking systems may temporarily lose tracking as they suffer by occlusion and blind spots. A possible solution is to adopt a hybrid approach where the inside-out tracker of the HMD is augmented with an outside-in sensing system. On the other hand, when the tracking signal of the outside-in system is recovered after a loss of tracking the transition from inside-out tracking to hybrid tracking may generate a discontinuity, i.e a sudden change of the virtual viewpoint, that can be uncomfortable for the user. Therefore, hybrid tracking solutions for HMDs require advanced sensor fusion algorithms to obtain a smooth transition. This work proposes a method for hybrid tracking of a HMD with smooth transitions based on an adaptive complementary filter. The proposed approach can be configured with several parameters that determine a trade-off between user experience and tracking error. A user study was carried out in a room-scale virtual reality environment, where users carried out two different tasks while multiple signal tracking losses of the outside-in sensor system occurred. The results show that the proposed approach improves user experience compared to a standard Extended Kalman Filter, and that tracking error is lower compared to a state-of-the-art complementary filter when configured for the same quality of user experience.

This paper presents a robot system for manipulation and picking of tomato fruits guided by computer vision. A CNN algorithm trained on a custom image dataset is used for fruit detection and the depth camera enables position estimation. The robot manipulator is equipped with a commercial soft gripper for picking fragile objects. Three planning procedures have been proposed to successfully reach and grasp the tomatoes. Experiments on simulated crops have compared the effectiveness of the proposed procedures.

This work addresses the task of robot depalletizing by means of a mobile manipulator, taking into account the problem of localizing the boxes to be removed from the pallet and a manipulation strategy that allows to pull the boxes without lifting them with the robot arm. The depalletizing task is of particular interest in the industrial scenario in order to increase efficiency, flexibility and economic affordability of automatic warehouses.The proposed solution makes use of a multi-sensor vision system and a force-controlled collaborative robot in order to detect the boxes on the pallet and to control the robot interaction with the boxes to be removed. The vision system comprises a fixed 3D Time-of-flight camera and an eye-in-hand 2D camera. Preliminary experimental results performed on a laboratory setup with a fixed-based robotic manipulator are reported to show the effectiveness of the perception and control system.

The level of adoption of Precision Agriculture (PA) technologies is still very different from one country to another and from one region to another in the same country. A major challenge is to develop PA from a best practice pursued by a minority of enlightened farmers to a widespread practice with sizeable impact on the use of environmental resources. One of the obstacles hindering PA is the lack of quantitative data readily accessible to farmers to guide their daily operations. In this paper, we present the information system developed within project POSITIVE to support and enhance precision irrigation across the whole Emilia-Romagna region. To this purpose, the POSITIVE information system establishes a service transforming satellite and sensor data into biophysical parameters and vegetation indices with full regional coverage. These data are automatically fed into a public irrigation advisory service (Irrinet+) thereby enabling precision irrigation and fertigation on a regional scale. Irrigation maps can be sent as advice to farmers or directly commanded to registered irrigation machines. The architecture of the distributed information system and the open protocols developed to achieve scalability and enable interaction of multiple heterogeneous components are reported in the paper.

Place recognition based on landmarks or features is an important problem occurring in localization, mapping, computer vision and point cloud processing. In this paper, we present GLAROT-3D, a translation and rotation invariant 3D signature based on geometric relations. The proposed method encodes into a histogram the pairwise relative positions of keypoint features extracted from 3D sensor data. Since it relies only on geometric properties and not on specific feature descriptors, it does not require any prior training or vocabulary construction and enables lightweight comparisons between landmark maps. The similarity of two point maps is computed as the distance between the corresponding rotated histograms to achieve rotation invariance. Histogram rotation is enabled by efficient orientation histogram based on sphere cubical projection. The performance of GLAROT has been assessed through experiments with standard benchmark datasets.

This paper describes the design and evaluation of a vision system conceived to provide perception in Autonomous Underwater Vehicle (AUV) intervention tasks. Due to the accuracy requirements inherent in manipulation tasks, high performance vision systems, enabling adequate perception capabilities, are needed to cope with underwater interventions. However, vision systems are challenged by the difficulties and variability of underwater environments as well as by the need to operate in a sealed canister. The vision system described in this paper addresses design issues like computational performance, energy power consumption, heat dissipation, and network capabilities. Even though the system has been designed to support stereovision, experiments in several underwater contexts have shown that stereovision is seldom applicable, due to the many problems faced by light propagation in water. Developing a system for underwater operation emphasizes the need for tradeoffs between computational performance and power consumption and dissipation, as well as the need for flexibility to support multiple vision processing pipelines and adapt to the specific underwater context.

Keypoint features detection from measurements enables efficient localization and map estimation through the compact representation and recognition of locations. The keypoint detector FALKO has been proposed to detect stable points in laser scans for localization and mapping tasks. In this paper, we present novel loop closure methods based on FALKO keypoints and compare their performance in online localization and mapping problems. The pose graph formulation is adopted, where each pose is associated to a local map of keypoints extracted from the corresponding laser scan. Loops in the graph are detected by matching local maps in two steps. First, the candidate matching scans are selected by comparing the scan signatures obtained from the keypoints of each scan. Second, the transformation between two scans is obtained by pairing and aligning the respective keypoint sets. Experiments with standard benchmark datasets assess the performance of FALKO and of the proposed loop closure algorithms in both offline and online localization and map estimation.

This work proposes a method for autonomous robot exploration of unknown objects by sensor fusion of 3D range data. The approach aims at overcoming the physical limitation of the minimum sensing distance of range sensors. Two range sensors are used with complementary characteristics mounted in eye-in-hand configuration on a robot arm. The first sensor operates at mid-range and is used in the initial phase of exploration when the environment is unknown. The second sensor, which provides short-range data, is used in the following phase where the objects are explored at close distance through next best view planning. Next best view planning is performed using a volumetric representation of the environment. A complete point cloud model of each object is finally computed by global registration of all object observations including mid-range and short range views. In experiments performed in environments with multiple rigid objects the global registration algorithm has proven more accurate than a standard sequential registration approach.

Object category recognition and localization in 3D range data is of great importance in robot manipulation. In this work we propose a novel approach for object categorization and grasping that is focused on topological shape segmentation. The method allows generation of watertight triangulated models of the objects and their shape segmentation into parts. This segmentation provides meaningful information about grasp affordances. An efficient technique for encoding proximity data from range scans is also presented as well as an advanced strategy for manipulation of object sub-parts. Experiments are reported in a real environment using a robot arm equipped with eye-in-hand laser scanner and a parallel gripper.

Loop closure is one of the most difficult task in localization and mapping problems since it suffers from perceptual aliasing. Multi-hypothesis topological SLAM algorithms have been developed to exploit connectivity and disambiguate such difficult task. In this paper, we propose a multi-hypothesis constraint network algorithm that tracks multiple map topologies and simultaneously keeps metric information. The map is stored as a graph consisting of poses and constraints and each constraint is associated to a loop closure hypothesis. Hypotheses are stored in a hypothesis tree that is expanded whenever possible loop closure may occur. Network poses are computed according to the most likely topological configuration, but alternative pose values are also computed for the poses that are adjacent to a hypothesis constraint to recover quickly the new configuration when required. Results provide a validation of the proposed approach.

In the last decade, several algorithms, usually based on information filtering techniques, have been proposed to address multi-robot mapping problem. Less interest has been devoted to investigate a parallel or distributed organization of such algorithms in the perspective of multi-robot exploration. In this paper, we propose a distributed algorithm for map estimation based on Gauss-Seidel relaxation. The complete map is shared among independent tasks running on each robot, which integrate the independent robot measurements in local submaps, and a server, which stores contour nodes separating the submaps. Each task updates its local submap and periodically checks for inter-robot data associations. Gauss-Seidel relaxation is performed independently on each robot and afterwards on the contour nodes set on the server. Results illustrate the potential and flexibility of the new approach.

Several recent algorithms address simultaneous localization and mapping as a maximum likelihood problem. While many proposed methods focus on efficiency or on online computation, less interest has been devoted to investigate a parallel or distributed organization of such algorithms in the perspective of multi-robot exploration. In this paper, we propose a parallel algorithm for map estimation based on Gauss-Seidel relaxation. The map is given in the form of a constraints network and is partioned into clusters of nodes by applying a node-tearing technique. The identified clusters of nodes can be processed independently as tasks assigned to different processors. The graph decomposition induces also a hierarchical organization of nodes that could be exploited for more sophisticated relaxation techniques. Results illustrate the potential and flexibility of the new approach.

In this paper, we address the problem of incrementally optimizing constraint networks for maximum likelihood map learning. Our approach allows a robot to efficiently compute configurations of the network with small errors while the robot moves through the environment. We apply a variant of stochastic gradient descent and use a tree-based parameterization of the nodes in the network. By integrating adaptive learning rates in the parameterization of the network, our algorithm can use previously computed solutions to determine the result of the next optimization run. Additionally, our approach updates only the parts of the network which are affected by the newly incorporated measurements and starts the optimization approach only if the new data reveals inconsistencies with the network constructed so far. These improvements yield an efficient solution for this class of online optimization problems. Our approach has been implemented and tested on simulated and on real data. We present comparisons to recently proposed online and offline methods that address the problem of optimizing constraint network. Experiments illustrate that our approach converges faster to a network configuration with small errors than the previous approaches.