Object In Unknown Environment Research Articles

An Efficient Object Navigation Strategy for Mobile Robots Based on Semantic Information

In recent years, the rapid development of computer vision makes it possible for mobile robots to be more intelligent. Among the related technologies, the visual SLAM system allows the mobile robot to locate itself, build the map, and provide a navigation strategy to execute follow-up tasks, such as searching for objects in unknown environment according to the observed information. However, most of the existing studies are meant to provide a predefined trajectory for the robot or allow the robot to explore blindly and randomly, which undoubtedly affects the efficiency of the object navigation process and goes against with the idea of “intelligent”. To solve the above problems, an efficient object navigation strategy is proposed in this paper. Firstly, a semantic association model is obtained by using the Mask R-CNN and skip-gram to conduct correlation analysis of common indoor objects. Then, with the help of the above model and ROS framework, an effective object navigation strategy is designed to enable the robot to find the given target efficiently. Finally, the classical ORB-SLAM2 system method is integrated to help the robot build a high usability environment map and find passable paths when moving. Simulation results validated that the proposed strategy can efficiently help the robot to navigate to the object without human intervention.

Searching Behavior in the Tropical Fire Ant Solenopsis geminata (Hymenoptera: Formicidae).

Social insects have evolved different search strategies to find target objects in unknown environments. In the present study, the searching behavior of the tropical fire ant Solenopsis geminata was investigated in a circular arena. The average time, search path, speed, and search patterns of worker ants in a circular arena were determined. The results showed that fire ant workers followed six major search patterns. The variation in the searching patterns of workers may explain the different levels of exploration. Most workers (56.8%) tended to search in small loops and progressively increase the search area size. These workers mostly turned in one direction, either clockwise or counterclockwise. More workers turned in a consistent pattern than in an inconsistent pattern. Moving speed was also higher in workers that maintained their turning directions than in those that changed directions. We thus propose that following search patterns consisting of loops of increasing size may be an effective strategy. The tropical fire ant S. geminata is a globally invasive species that was introduced to Taiwan 40 years ago and has continued to threaten residents. Based on behavioral studies of S. geminata, we may gain a better understanding of their exploratory behavior in the ecosystem in Taiwan.

Detection and Segmentation of Unlearned Objects in Unknown Environment

Detecting and segmenting unlearned objects in unknown environment is a very important visual perception ability to enhance industrial intelligence. In this article, we present a novel conditional random field model integrating unimodal and cross-modal terms for detecting and segmenting object instances without knowing their categories and without sampling extra proposals. This model takes a paired image and point cloud as input, from which we first develop a set of novel category-independent features to distinguish objects. Then, a set of unary, pairwise, and higher order potentials are designed according to these category-independent features, and the cross-modal potential is introduced as a novel global constraints to keep the spatial consistency in both 2-D and 3-D modalities. In this novel model, the unlearned object detection and segmentation is treated as the process of pixel labeling. Thus, adjacent or occlusion object instances can also be separated efficiently from a labeled map. By comparison with the baseline methods, experimental results on a public RGB+D dataset show that the proposed model can obtain better performance with improved precision and recall rate. Moreover, we use the proposed method in a real industrial scene and achieve satisfactory performance.

Attention-based active visual search for mobile robots

We present an active visual search model for finding objects in unknown environments. The proposed algorithm guides the robot towards the sought object using the relevant stimuli provided by the visual sensors. Existing search strategies are either purely reactive or use simplified sensor models that do not exploit all the visual information available. In this paper, we propose a new model that actively extracts visual information via visual attention techniques and, in conjunction with a non-myopic decision-making algorithm, leads the robot to search more relevant areas of the environment. The attention module couples both top-down and bottom-up attention models enabling the robot to search regions with higher importance first. The proposed algorithm is evaluated on a mobile robot platform in a 3D simulated environment. The results indicate that the use of visual attention significantly improves search, but the degree of improvement depends on the nature of the task and the complexity of the environment. In our experiments, we found that performance enhancements of up to 42% in structured and 38% in highly unstructured cluttered environments can be achieved using visual attention mechanisms.

Optimized Self-Localization for SLAM in Dynamic Scenes Using Probability Hypothesis Density Filters

In many applications, sensors that map the positions of objects in unknown environments are installed on dynamic platforms. As measurements are relative to the observer's sensors, scene mapping requires accurate knowledge of the observer state. However, in practice, observer reports are subject to positioning errors. Simultaneous localization and mapping addresses the joint estimation problem of observer localization and scene mapping. State-of-the-art approaches typically use visual or optical sensors and therefore rely on static beacons in the environment to anchor the observer estimate. However, many applications involving sensors that are not conventionally used for Simultaneous Localization and Mapping (SLAM) are affected by highly dynamic scenes, such that the static world assumption is invalid. This paper proposes a novel approach for dynamic scenes, called GEneralized Motion (GEM) SLAM. Based on probability hypothesis density filters, the proposed approach probabilistically anchors the observer state by fusing observer information inferred from the scene with reports of the observer motion. This paper derives the general, theoretical framework for GEM-SLAM, and shows that it generalizes existing Probability Hypothesis Density (PHD)-based SLAM algorithms. Simulations for a model-specific realization using range-bearing sensors and multiple moving objects highlight that GEM-SLAM achieves significant improvements over three benchmark algorithms.

Real-time interactive modeling and scalable multiple object tracking for AR

We propose a real-time solution for modeling and tracking multiple 3D objects in unknown environments for Augmented Reality. The proposed solution consists of both scalable tracking and interactive modeling. Our contribution is twofold: First, we show how to scale with the number of objects using keyframes. This is done by combining recent techniques for image retrieval and online Structure from Motion, which can be run in parallel. As a result, tracking 50 objects in 3D can be done within 6–35ms per frame, even under difficult conditions for tracking. Second, we propose a method to let the user add new objects very quickly. The user simply has to select in an image a 2D region lying on the object. A 3D primitive is then fitted to the features within this region, and adjusted to create the object 3D model. We demonstrate the modeling of polygonal and circular-based objects. In practice, this procedure takes less than a minute.

Natural steering behaviors for virtual pedestrians

The animation of humanoids in real-time applications is yet a challenge if the problem involves attaining a precise location in a virtual world (path-planning), moving realistically according to its own personality, intentions and mood (motion planning). In this paper we propose a formally complete and low-cost solution based upon boundary value problems (BVP) to control steering behaviors of characters in dynamic environments. We use a potential field formalism that allows synthetic actors to move negotiating space, avoiding collisions, and attaining goals, while producing very individual paths. The individuality of each character can be set by changing its inner field parameters leading to a broad range of possible behaviors without jeopardizing its performance. To illustrate the technique potentialities, some results exploring situations as steering behavior in corridors with collision avoidance and competition for a goal, and searching for objects in unknown environments are presented and discussed. A proposal to automatically change the size of the field of view of each agent, producing different behaviors is also a contribution of this paper. Some comments about performance are also made to help the reader to evaluate the potential of the method.