Movable Obstacles Research Articles

An Evaluation Framework of Human-Robot Teaming for Navigation Among Movable Obstacles via Virtual Reality-Based Interactions

An Evaluation Framework of Human-Robot Teaming for Navigation Among Movable Obstacles via Virtual Reality-Based Interactions

Interacting with Obstacles Using a Bio-Inspired, Flexible, Underactuated Multilink Manipulator.

With the increasing demand for robotic manipulators to operate in complex environments, it is important to develop designs that work in obstacle-rich environments and can navigate around obstacles. This paper aims to demonstrate the capabilities of a bio-inspired, underactuated multilink manipulator in environments with fixed and/or movable obstacles. To simplify the system design, a single rotational actuator is used at the base of the manipulator. We present a modeling method for flexible, multilink underactuated manipulators, including their interaction with obstacles. We also demonstrate how to plan a trajectory for the manipulator in environments with fixed obstacles. The robustness of the manipulator is examined by analyzing the effects of uncertainty in its initial state and the position of obstacles. Next, we demonstrate the performance of the manipulator in environments with movable obstacles and show the advantages of controlling the obstacles' radii and positions. Lastly, we showcase the process of picking up an object in workspaces with obstacles. All the findings are supported by simulations as well as hardware experiments.

Tactile‐Based Negotiation of Unknown Objects during Navigation in Unstructured Environments with Movable Obstacles

Traditional robot navigation passively plans/replans to avoid any contact with obstacles in the scene. This limits the obtained solutions to the collision‐free space and leads to failures if the path to the goal is obstructed. In contrast, humans actively modify their environment by repositioning objects if it assists locomotion. This article aims to bring robots closer to such abilities by providing a framework to detect and clear movable obstacles to continue navigation. The approach leverages a multimodal robot skin that provides both local proximity and tactile feedback regarding physical interactions with the surroundings. This multimodal contact feedback is employed to adapt the robot's behavior when interacting with object surfaces and regulating applied forces. This enables the robot to remove bulky obstacles from its path and solves otherwise infeasible navigation problems. The system's ability is demonstrated in simulation and real‐world scenarios involving movable and nonmovable obstacles.

Breathing sounds analysis system for early detection of airway problems in patients with a tracheostomy tube

To prevent immediate mortality in patients with a tracheostomy tube, it is essential to ensure timely suctioning or replacement of the tube. Breathing sounds at the entrance of tracheostomy tubes were recorded with a microphone and analyzed using a spectrogram to detect airway problems. The sounds were classified into three categories based on the waveform of the spectrogram according to the obstacle status: normal breathing sounds (NS), vibrant breathing sounds (VS) caused by movable obstacles, and sharp breathing sounds (SS) caused by fixed obstacles. A total of 3950 breathing sounds from 23 patients were analyzed. Despite neither the patients nor the medical staff recognizing any airway problems, the number and percentage of NS, VS, and SS were 1449 (36.7%), 1313 (33.2%), and 1188 (30.1%), respectively. Artificial intelligence (AI) was utilized to automatically classify breathing sounds. MobileNet and Inception_v3 exhibited the highest sensitivity and specificity scores of 0.9441 and 0.9414, respectively. When classifying into three categories, ResNet_50 showed the highest accuracy of 0.9027, and AlexNet showed the highest accuracy of 0.9660 in abnormal sounds. Classifying breathing sounds into three categories is very useful in deciding whether to suction or change the tracheostomy tubes, and AI can accomplish this with high accuracy.

Experimental and numerical study of heavy gas dispersion in presence of obstacle motion

Most of the current research on heavy gas dispersion focuses on how fixed obstacles affect gas spreading. The turbulence caused by the movements of people or traffic will significantly affect heavy gas dispersion. Accordingly, this study presents an investigation of heavy gas dispersion under the influence of moving obstacles, which is based on the dynamic mesh approach using computational fluid dynamics (CFD). A turbulence model suitable for such a condition has been developed, and we have designed a small-scale experiment to verify the model's viability. Consequently, the verified model is further applied to a full-scale scenario for a chemical factory where a chlorine leak triggers an evacuation movement. On the basis of this scenario, we simplify the massive escape crowd to a regular geometric model, and the effects of the speed and size of movable obstacles on gas dispersion have been investigated by means of the RNG k-ε model and the layering updating approach in the dynamic mesh.

Aerial online mapping on‐board system by real‐time object detection for UGV path generation in unstructured outdoor environments

AbstractAn optimal path provides efficient operation of unmanned ground vehicles (UGVs) for many kinds of tasks such as transportation, exploration, surveillance, and search and rescue in unstructured areas that include various unexpected obstacles. Various onboard sensors such as LiDAR, radar, sonar, and cameras are used to detect obstacles around the UGVs. However, their range of view is often limited by movable obstacles or barriers, resulting in inefficient path generation. Here, we present the aerial online mapping system to generate an efficient path for a UGV on a two‐dimensional map. The map is updated by projecting obstacles detected in the aerial images taken by an unmanned aerial vehicle through an object detector based on a conventional convolutional neural network. The proposed system is implemented in real‐time by a skid steering ground vehicle and a quadcopter with relatively small, low‐cost embedded systems. The frameworks and each module of the systems are given in detail to evaluate the performance. The system is also demonstrated in unstructured outdoor environments such as in a football field and a park with unreliable communication links. The results show that the aerial online mapping is effective in path generation for autonomous UGVs in real environments.

Curriculum Reinforcement Learning From Avoiding Collisions to Navigating Among Movable Obstacles in Diverse Environments

Curriculum learning has proven highly effective to speed up training convergence with improved performance in a variety of tasks. Researchers have been studying how a curriculum can be constituted to train reinforcement learning (RL) agents in various application domains. However, discovering curriculum sequencing requires the ranking of sub-tasks or samples in order of difficulty, which is not yet sufficiently studied for robot navigation problems. It is still an open question what navigation strategies can be learned and transferred during multi-stage transfer learning from easy to hard. Furthermore, despite of some attempts of learning real robot manipulation tasks using curriculum, most of existing works are limited to toy or simulated settings rather than realistic scenarios. To address those issues, we first investigated how the model convergence in diverse environments relates to the navigation strategies and difficulty metrics. We found that only some of the environments can be trained from scratch, such as in a relatively open tunnel-like environment that only required wall following. We then carried out a two-stage transfer learning for more difficult environments. We found such approach effective for goal navigation, but failed for more complex tasks where movable obstacles may be on the navigation path. To facilitate more complex policies in the navigation among movable obstacles (NAMO) task, another curriculum with distance and pace functions appropriate to the difficulty of the environment was developed. The proposed scheme was proved effective and the strategies learned were discussed via comprehensive evaluations conducted in simulated and real environments. Supplementary materials can be found at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://arg-nctu.github.io/projects/curl-navi.html</uri>

English

Autonomous vehicles in public transport can perform a wide range of real-world tasks such as: moving in factories, in public transport, in search and rescue, etc., thus requiring varying degrees of auto-navigation in response to changes in the environment. This paper presents the predictive model (MPC) for the active suspension system, the vehicle's damping system, combined with Deep Q-network (DQN) algorithm reinforcement learning method applied to control self-driving cars in public transport. Intelligent traffic control system to control movement to avoid fixed obstacles or movable obstacles in the event of external interference, taking into account the comfort of the occupants of the vehicle; taking into account the load, the conveying systems; for the purpose of application in the field of intelligent transportation. The research results, built on Matlab Simulink software, show that autonomous vehicles can safely complete intelligent navigation tasks in an unknown environment and become a real system intelligent with the ability to self-study and adapt well to many different environments and various nonlinear factors.

Navigation Among Movable Obstacles via Multi-Object Pushing Into Storage Zones

With the majority of mobile robot path planning methods being focused on obstacle avoidance, this paper, studies the problem of Navigation Among Movable Obstacles (NAMO) in an unknown environment, with static (i.e., that cannot be moved by a robot) and movable (i.e., that can be moved by a robot) objects. In particular, we focus on a specific instance of the NAMO problem in which the obstacles have to be moved to predefined storage zones. To tackle this problem, we propose an online planning algorithm that allows the robot to reach the desired goal position while detecting movable objects with the objective to push them towards storage zones to shorten the planned path. Moreover, we tackle the challenging problem where an obstacle might block the movability of another one, and thus, a combined displacement plan needs to be applied. To demonstrate the new algorithm’s correctness and efficiency, we report experimental results on various challenging path planning scenarios. The presented method has significantly better time performance than the baseline, while also introducing multiple novel functionalities for the NAMO problem.

Construction of indoor obstacle element map based on scene-aware priori obstacle rules

An obstacle element map is the basis of indoor navigation space subdivision. Effective and reasonable indoor space subdivision can improve the fineness of indoor navigation path planning. To divide an indoor navigation space more finely, an indoor obstacle element map construction method based on scene-aware a priori rules for obstacles is proposed. This method divides indoor space into navigable space (N-space), semi-navigable space (SN-space), and non-navigable space (NN-space) based on the flexible space subdivision framework (FSS) and classifies indoor obstacles into four categories, walls, doors, movable obstacles (MOs), and immovable obstacles (IMOs). First, by analyzing the layout and mobility of common indoor elements, the obstacle prior rules for seven types of indoor scenes (including hospitals, residences, classrooms, office buildings, transportation hubs, restaurants, and shopping malls) are formulated, and a method for obtaining obstacle prior rules based on scene recognition is proposed. Then, obstacles and their mobility are extracted from the semantic segmentation results of point clouds based on the acquired rules and mobility indicators. Finally, the extracted obstacles are processed to construct the obstacle element map, wall and door elements are fitted by the random sample consensus (RANSAC) algorithm, and IMOs and MOs are processed by Euclidean clustering. The experimental results show that the proposed method can effectively determine four types of indoor obstacles, and the overall accuracy in simple scenes is 85.22 %, while in complex scenes it is 97.96 %. Under the experimental environment (CPU: Intel Core i7-7700K; Memory: 16 GB and 2400 MHz; OS: Win10) in this paper, the construction of a simple scene obstacle element map can be completed in 5 s. In addition to the spatial information of the indoor elements, the obstacle element map also contains information about whether the elements can be moved, which provides the basis for the subdivision of the indoor space.

Enabling Cooperative Relay Selection by Transfer Learning for the Industrial Internet of Things

Large manufacturing sites with movable obstacles and dynamic network topology call for reliable and efficient strategies to transmit data through the industrial Internet of Things (IoT). Cooperative communications and relay selection have shown a great potential to improve throughput and energy efficiency at the expanse of high end-to-end transmission latency. To reduce this latency, we propose to use transfer learning for relay selection in the industrial IoT. Unlike traditional approaches that are trained for a specific task, transfer learning exploits the acquired knowledge from similar tasks to assist new tasks. Transfer learning is capable of improving learning performance, reducing the need for large datasets for different setups, lowering communication overhead and computational complexity. Specifically, in this paper, we propose a generic transfer learning framework for relay selection problems in the industrial IoT. Based on the proposed framework, we design a hypothesis and test it by empirical data for convergence analysis. Also, we devise and conduct a step-by-step and rigorous hyperparameter tuning procedure for the proposed transfer learning framework. The accuracy of the proposed approach is evaluated and verified by extensive training and test datasets abiding by different statistical distributions.

Passenger emergency evacuation from bus carriage: Results from realistic data and modeling simulations

One of critical challenges in the development of pedestrian models is the lack of relevant data under emergency conditions. In this paper, we reveal several behavior characteristics of passenger emergency evacuation from a burning bus carriage, by observing and analyzing a video recording, attempting to close the gap between practical observation and theoretical modeling. The analysis results show that there are considerable differences between real emergency evacuation and experimental normal evacuation with respect to the cumulative flows, flows, and time gap distributions. Additionally, the behavior of falling-down, which contributes to the formation of movable obstacles, interrupts the continuity of the evacuation process. Then, we incorporate these behavioral characteristics into a microscopic pedestrian model with a fine lattice space representation. The simulation results indicate that the escape is slowed down by the falling behavior, as well as by the luggage-carrying behavior.

Reconfigurable and Agile Legged-Wheeled Robot Navigation in Cluttered Environments With Movable Obstacles

Legged and wheeled locomotion are two standard methods used by robots to perform navigation. Combining them to create a hybrid legged-wheeled locomotion results in increased speed, agility, and reconfigurability for the robot, allowing it to traverse a multitude of environments. The CENTAURO robot has these advantages, but they are accompanied by a higher-dimensional search space for formulating autonomous economical motion plans, especially in cluttered environments. In this article, we first review our previously presented legged-wheeled footprint reconfiguring global planner. We describe the two incremental prototypes, where the primary goal of the algorithms is to reduce the search space of possible footprints such that plans that expand the robot over the low-lying wide obstacles or narrow into passages can be computed with speed and efficiency. The planner also considers the cost of avoiding obstacles versus negotiating them by expanding over them. The second part of this article presents our new work on local obstacle pushing, which further increases the number of tight scenarios the planner can solve. The goal of the new local push-planner is to place any movable obstacle of unknown mass and inertial properties, obstructing the previously planned trajectory from our global planner, to a location devoid of obstruction. This is done while minimising the distance traveled by the robot, the distance the object is pushed, and its rotation caused by the push. Together, the local and global planners form a major part of the agile reconfigurable navigation suite for the legged-wheeled hybrid CENTAURO robot.

Representation, learning, and planning algorithms for geometric task and motion planning

We present a framework for learning to guide geometric task-and-motion planning (G-TAMP). G-TAMP is a subclass of task-and-motion planning in which the goal is to move multiple objects to target regions among movable obstacles. A standard graph search algorithm is not directly applicable, because G-TAMP problems involve hybrid search spaces and expensive action feasibility checks. To handle this, we introduce a novel planner that extends basic heuristic search with random sampling and a heuristic function that prioritizes feasibility checking on promising state–action pairs. The main drawback of such pure planners is that they lack the ability to learn from planning experience to improve their efficiency. We propose two learning algorithms to address this. The first is an algorithm for learning a rank function that guides the discrete task-level search, and the second is an algorithm for learning a sampler that guides the continuous motion-level search. We propose design principles for designing data-efficient algorithms for learning from planning experience and representations for effective generalization. We evaluate our framework in challenging G-TAMP problems, and show that we can improve both planning and data efficiency.

Multi-Agent Terraforming: Efficient Multi-Agent Path Finding via Environment Manipulation

Planning collision-free paths for multiple agents operating in close proximity has a myriad of applications ranging from smart warehouses to route planning for airport taxiways. This problem, known as the Multi-Agent Path-Finding (MAPF) problem, is highly relevant to real-world applications in automation and robotics, and has attracted significant research in recent years. While in many applications, the robots are tasked with transporting objects and thus have the means to move obstacles, common formulations of the problem prohibit agents from moving obstacles en-route to a task. This often causes agents to take long detours to avoid obstacles instead of simply moving them to clear a path. In this work we present multi-agent terraforming, a novel extension of the MAPF problem that can exploit the fact that the system contains movable obstacles. We build upon leading MAPF solvers and propose an efficient method to solve the multi-agent terraforming problem in a manner that is both complete and optimal. We evaluate our method on scenarios inspired by smart warehouses (such as those of Amazon) and demonstrate that, compared to the classical MAPF formulation, the extra flexibility provided by terraforming facilitates a notable improvement of solution quality.

Path Planning and Real-Time Collision Avoidance Based on the Essential Visibility Graph

This paper deals with a novel procedure to generate optimum flight paths for multiple unmanned aircraft in the presence of obstacles and/or no-fly zones. A real-time collision avoidance algorithm solving the optimization problem as a minimum cost piecewise linear path search within the so-called Essential Visibility Graph (EVG) is first developed. Then, a re-planning procedure updating the EVG over a selected prediction time interval is proposed, accounting for the presence of multiple flying vehicles or movable obstacles. The use of Dubins curves allows obtaining smooth paths, compliant with flight mechanics constraints. In view of possible future applications in hybrid scenarios where both manned and unmanned aircraft share the airspace, visual flight rules compliant with International Civil Aviation Organization (ICAO) Annex II Right of Way were implemented. An extensive campaign of numerical simulations was carried out to test the effectiveness of the proposed technique by setting different operational scenarios of increasing complexity. Results show that the algorithm is always able to identify trajectories compliant with ICAO rules for avoiding collisions and assuring a minimum safety distance as well. Furthermore, the low computational burden suggests that the proposed procedure can be considered a promising approach for real-time applications.

Arduino Based Obstacle Detecting System

Water is an object detecting system which uses radio waves to determine the range, angle and distance of the obstacle from the detecting system. In this paper we used ultrasonic sensor to transmit pulses of radio waves or microwaves which bounce off any object in their path. Arduino is a single- board micro controller to make multiple accessories support easily with low cost. The main aim of this paper was detecting both movable and immovable obstacles which are present in particular range by using processing IDE software and also known about the detected obstacle image by using camera. This system was controlled by using Bluetooth controlled car.

Simulation-based optimization of inner layout of a theater considering the effect of pedestrians**Project supported by the National Natural Science Foundation of China (Grant Nos. 11572184 and 11562020), the National Basic Research Program of China (Grant No. 2012CB725404), and the Research Foundation of Shanghai Institute of Technology (Grant No. 39120K196008- A06).

We propose an extended cellular automaton model based on the floor field. The floor field can be changed accordingly in the presence of pedestrians. Furthermore, the effects of pedestrians with different speeds are distinguished, i.e., still pedestrians result in more increment of the floor field than moving ones. The improved floor field reflects impact of pedestrians as movable obstacles on evacuation process. The presented model was calibrated by comparing with previous studies. It is shown that this model provides a better description of crowd evacuation both qualitatively and quantitatively. Then we investigated crowd evacuation from a middle-size theater. Four possible designs of aisles in the theater are studied and one of them is the actual design in reality. Numerical simulation shows that the actual design of the theater is reasonable. Then we optimize the position of the side exit in order to reduce the evacuation time. It is shown that the utilization of the two exits at bottom is less than that of the side exits. When the position of the side exit is shifted upwards by about 1.6 m, it is found that the evacuation time reaches its minimum.

Mobile robot path planning in dynamic environment based on cuckoo optimization algorithm

Nowadays, the usage of autonomous mobile robots that fulfill various activities in enormous number of applications without human’s interference in a dynamic environment are thriving. A dynamic environment is the robot’s environment which is comprised of some static obstacles as well as several movable obstacles that their quantity and location change randomly through the time. Efficient path planning is one the significant necessities of these kind of robots to do their tasks effectively. Mobile robot path planning in a dynamic environment is finding a shortest possible path from an arbitrary starting point toward a desired goal point which needs to be safe (obstacle avoidance) and smooth as well as possible. To achieve this target, simultaneously satisfying a collection of certain constraints including the shortest, smooth, and collision free path is required. Therefore, this issue can be considered as an optimization problem, consequently solved via optimization algorithms. In this article, a new method based on cuckoo optimization algorithm is proposed for solving the mobile robot path planning problem in a dynamic environment. Furthermore, to diminish the computational complexity, the feature vector is also optimized (i.e. reduced in dimension) via a new proposed technique. The simulation results show the performance of proposed algorithm in finding a short, safe, smooth, and collision free path in different environment conditions.

Trade-off in the computation of minimum constraint removal paths for manipulation planning

Graphical