ABSTRACT
The widespread adoption of robotic technologies in healthcare has opened up new perspectives for enhancing accuracy, effectiveness and quality of medical procedures and patients' care. Special attention has been given to the reliability of robots when operating in environments shared with humans and to the users' safety, especially in case of mobile platforms able to navigate autonomously. From the analysis of the literature, it emerges that navigation tests carried out in a hospital environment are preliminary and not standardized. This paper aims to overcome the limitations in the assessment of autonomous mobile robots navigating in hospital environments by proposing: (i) a structured benchmarking protocol composed of a set of standardized tests, taking into account conditions with increasing complexity, (ii) a set of quantitative performance metrics. The proposed approach has been used in a realistic setting to assess the performance of two robotic platforms, namely HOSBOT and TIAGo, with different technical features and developed for different applications in a clinical scenario.
Subject(s)
Benchmarking , Hospitals , Robotics , Benchmarking/methods , Robotics/methods , HumansABSTRACT
Cognitive scientists believe that adaptable intelligent agents like humans perform spatial reasoning tasks by learned causal mental simulation. The problem of learning these simulations is called predictive world modeling. We present the first framework for a learning open-vocabulary predictive world model (OV-PWM) from sensor observations. The model is implemented through a hierarchical variational autoencoder (HVAE) capable of predicting diverse and accurate fully observed environments from accumulated partial observations. We show that the OV-PWM can model high-dimensional embedding maps of latent compositional embeddings representing sets of overlapping semantics inferable by sufficient similarity inference. The OV-PWM simplifies the prior two-stage closed-set PWM approach to the single-stage end-to-end learning method. CARLA simulator experiments show that the OV-PWM can learn compact latent representations and generate diverse and accurate worlds with fine details like road markings, achieving 69 mIoU over six query semantics on an urban evaluation sequence. We propose the OV-PWM as a versatile continual learning paradigm for providing spatio-semantic memory and learned internal simulation capabilities to future general-purpose mobile robots.
ABSTRACT
In the domain of mobile robot navigation, conventional path-planning algorithms typically rely on predefined rules and prior map information, which exhibit significant limitations when confronting unknown, intricate environments. With the rapid evolution of artificial intelligence technology, deep reinforcement learning (DRL) algorithms have demonstrated considerable effectiveness across various application scenarios. In this investigation, we introduce a self-exploration and navigation approach based on a deep reinforcement learning framework, aimed at resolving the navigation challenges of mobile robots in unfamiliar environments. Firstly, we fuse data from the robot's onboard lidar sensors and camera and integrate odometer readings with target coordinates to establish the instantaneous state of the decision environment. Subsequently, a deep neural network processes these composite inputs to generate motion control strategies, which are then integrated into the local planning component of the robot's navigation stack. Finally, we employ an innovative heuristic function capable of synthesizing map information and global objectives to select the optimal local navigation points, thereby guiding the robot progressively toward its global target point. In practical experiments, our methodology demonstrates superior performance compared to similar navigation methods in complex, unknown environments devoid of predefined map information.
ABSTRACT
-This paper presents a new control methodology for achieving smooth gait transitions for a hexapod robot using Central Pattern Generators (CPGs). The approach involves modifying the Phase Oscillator within the CPG network to enable smooth transitions between different gaits in order to improve the adaptability to changing environmental conditions. The foot trajectory generator is designed based on the CPG output, allowing the possibility of online adjustment of foot trajectory parameters, such as step height and size, as well as the robot's speed and direction. Our simulation demonstrates the effectiveness of the modified oscillator in achieving smoother gait transitions with a transition time falls close to the output period of the CPG oscillators, and experiments on a real hexapod robot validate the feasibility and efficiency of our approach in considering online adjustability of trajectory parameters, confirming the potential of this methodology to enhance the locomotion capabilities of legged robots for navigating complex terrains.
ABSTRACT
The traditional Model-Based Reinforcement Learning (MBRL) algorithm has high computational cost, poor convergence, and poor performance in robot spatial cognition and navigation tasks, and it cannot fully explain the ability of animals to quickly adapt to environmental changes and learn a variety of complex tasks. Studies have shown that vicarious trial and error (VTE) and the hippocampus forward prediction mechanism in rats and other mammals can be used as key components of action selection in MBRL to support "goal-oriented" behavior. Therefore, we propose an improved Dyna-Q algorithm inspired by the forward prediction mechanism of the hippocampus to solve the above problems and tackle the exploration-exploitation dilemma of Reinforcement Learning (RL). This algorithm alternately presents the potential path in the future for mobile robots and dynamically adjusts the sweep length according to the decision certainty, so as to determine action selection. We test the performance of the algorithm in a two-dimensional maze environment with static and dynamic obstacles, respectively. Compared with classic RL algorithms like State-Action-Reward-State-Action (SARSA) and Dyna-Q, the algorithm can speed up spatial cognition and improve the global search ability of path planning. In addition, our method reflects key features of how the brain organizes MBRL to effectively solve difficult tasks such as navigation, and it provides a new idea for spatial cognitive tasks from a biological perspective.
ABSTRACT
Efficient obstacle-avoidance path planning is critical for orchards with numerous irregular obstacles. This paper presents a continuous bidirectional Quick-RRT* (CBQ-RRT*) algorithm based on the bidirectional RRT (Bi-RRT) and Quick-RRT* algorithms and proposes an expansion cost function that evaluates path smoothness and length to overcome the limitations of the Quick-RRT* algorithm for non-holonomic mobile robot applications. To improve the zigzag between dual trees caused by the dual-tree expansion of the Bi-RRT algorithm, CBQ-RRT* proposes the CreateConnectNode optimization method, which effectively solves the path smoothness problem at the junction of dual trees. Simulations conducted on the ROS platform showed that the CBQ-RRT* outperformed the unidirectional Quick-RRT* in terms of efficiency for various orchard layouts and terrain conditions. Compared to Bi-RRT*, CBQ-RRT* reduced the average path length and maximum heading angle by 8.5% and 21.7%, respectively. In addition, field tests confirmed the superior performance of the CBQ-RRT*, as evidenced by an average maximum path lateral error of 0.334 m, a significant improvement over Bi-RRT* and Quick-RRT*. These improvements demonstrate the effectiveness of the CBQ-RRT* in complex orchard environments.
ABSTRACT
Visual simultaneous localization and mapping (V-SLAM) plays a crucial role in the field of robotic systems, especially for interactive and collaborative mobile robots. The growing reliance on robotics has increased complexity in task execution in real-world applications. Consequently, several types of V-SLAM methods have been revealed to facilitate and streamline the functions of robots. This work aims to showcase the latest V-SLAM methodologies, offering clear selection criteria for researchers and developers to choose the right approach for their robotic applications. It chronologically presents the evolution of SLAM methods, highlighting key principles and providing comparative analyses between them. The paper focuses on the integration of the robotic ecosystem with a robot operating system (ROS) as Middleware, explores essential V-SLAM benchmark datasets, and presents demonstrative figures for each method's workflow.
ABSTRACT
The flexibility and versatility associated with autonomous mobile robots (AMR) have facilitated their integration into different types of industries and tasks. However, as the main objective of their implementation on the factory floor is to optimize processes and, consequently, the time associated with them, it is necessary to take into account the environment and congestion to which they are subjected. Localization, on the shop floor and in real time, is an important requirement to optimize the AMRs' trajectory management, thus avoiding livelocks and deadlocks during their movements in partnership with manual forklift operators and logistic trains. Threeof the most commonly used localization techniques in indoor environments (time of flight, angle of arrival, and time difference of arrival), as well as two of the most commonly used indoor localization methods in the industry (ultra-wideband, and ultrasound), are presented and compared in this paper. Furthermore, it identifies and compares three industrial indoor localization solutions: Qorvo, Eliko Kio, and Marvelmind, implemented in an industrial mobile platform, which is the main contribution of this paper. These solutions can be applied to both AMRs and other mobile platforms, such as forklifts and logistic trains. In terms of results, the Marvelmind system, which uses an ultrasound method, was the best solution.
ABSTRACT
This article is concerned with the path planning of mobile robots in dynamic environments. A new path planning strategy is proposed by integrating the improved ant colony optimization (ACO) and dynamic window approach (DWA) algorithms. An improved ACO is developed to produce a globally optimal path for mobile robots in static environments. Through improvements in the initialization of pheromones, heuristic function, and updating of pheromones, the improved ACO can lead to a shorter path with fewer turning points in fewer iterations. Based on the globally optimal path, a modified DWA is presented for the path planning of mobile robots in dynamic environments. By deleting the redundant nodes, optimizing the initial orientation, and improving the evaluation function, the modified DWA can result in a more efficient path for mobile robots to avoid moving obstacles. Some simulations are conducted in different environments, which confirm the effectiveness and superiority of the proposed path planning algorithms.
ABSTRACT
The leakage of gases and chemical vapors is a common accident in laboratory processes that requires a rapid response to avoid harmful effects if humans and instruments are exposed to this leakage. In this paper, the performance of a portable sensor node designed for integration with mobile and stationary robots used to transport chemical samples in automated laboratories was tested and evaluated. The sensor node has four main layers for executing several functions, such as power management, control and data preprocessing, sensing gases and environmental parameters, and communication and data transmission. The responses of three metal oxide semiconductor sensors, BME680, ENS160, and SGP41, integrated into the sensing layer have been recorded for various volumes of selected chemicals and volatile organic compounds, including ammonia, pentane, tetrahydrofuran, butanol, phenol, xylene, benzene, ethanol, methanol, acetone, toluene, and isopropanol. For mobile applications, the sensor node was attached to a sample holder on a mobile robot (ASTI ProBOT L). In addition, the sensor nodes were positioned close to automation systems, including stationary robots. The experimental results revealed that the tested sensors have a different response to the tested volumes and can be used efficiently for hazardous gas leakage detection and monitoring.
ABSTRACT
The ability to recognize the surface type is crucial for both indoor and outdoor mobile robots. Knowing the surface type can help indoor mobile robots move more safely and adjust their movement accordingly. However, recognizing surface characteristics is challenging since similar planes can appear substantially different; for instance, carpets come in various types and colors. To address this inherent uncertainty in vision-based surface classification, this study first generates a new, unique data set composed of 2,081 surface images (carpet, tiles, and wood) captured in different indoor environments. Secondly, the pre-trained state-of-the-art deep learning models, namely InceptionV3, VGG16, VGG19, ResNet50, Xception, InceptionResNetV2, and MobileNetV2, were utilized to recognize the surface type. Additionally, a lightweight MobileNetV2-modified model was proposed for surface classification. The proposed model has approximately four times fewer total parameters than the original MobileNetV2 model, reducing the size of the trained model weights from 42 MB to 11 MB. Thus, the proposed model can be used in robotic systems with limited computational capacity and embedded systems. Lastly, several optimizers, such as SGD, RMSProp, Adam, Adadelta, Adamax, Adagrad, and Nadam, are applied to distinguish the most efficient network. Experimental results demonstrate that the proposed model outperforms all other applied methods and existing approaches in the literature by achieving 99.52% accuracy and an average score of 99.66% in precision, recall, and F1-score. In addition to this, the proposed lightweight model was tested in real-time on a mobile robot in 11 scenarios consisting of various indoor environments such as offices, hallways, and homes, resulting in an accuracy of 99.25%. Finally, each model was evaluated in terms of model loading time and processing time. The proposed model requires less loading and processing time than the other models.
ABSTRACT
At the beginning of a project or research that involves the issue of autonomous navigation of mobile robots, a decision must be made about working with traditional control algorithms or algorithms based on artificial intelligence. This decision is not usually easy, as the computational capacity of the robot, the availability of information through its sensory systems and the characteristics of the environment must be taken into consideration. For this reason, this work focuses on a review of different autonomous-navigation algorithms applied to mobile robots, from which the most suitable ones have been identified for the cases in which the robot must navigate in dynamic environments. Based on the identified algorithms, a comparison of these traditional and DRL-based algorithms was made, using a robotic platform to evaluate their performance, identify their advantages and disadvantages and provide a recommendation for their use, according to the development requirements of the robot. The algorithms selected were DWA, TEB, CADRL and SAC, and the results show that-according to the application and the robot's characteristics-it is recommended to use each of them, based on different conditions.
ABSTRACT
Direct policy learning (DPL) is a widely used approach in imitation learning for time-efficient and effective convergence when training mobile robots. However, using DPL in real-world applications is not sufficiently explored due to the inherent challenges of mobilizing direct human expertise and the difficulty of measuring comparative performance. Furthermore, autonomous systems are often resource-constrained, thereby limiting the potential application and implementation of highly effective deep learning models. In this work, we present a lightweight DPL-based approach to train mobile robots in navigational tasks. We integrated a safety policy alongside the navigational policy to safeguard the robot and the environment. The approach was evaluated in simulations and real-world settings and compared with recent work in this space. The results of these experiments and the efficient transfer from simulations to real-world settings demonstrate that our approach has improved performance compared to its hardware-intensive counterparts. We show that using the proposed methodology, the training agent achieves closer performance to the expert within the first 15 training iterations in simulation and real-world settings.
ABSTRACT
This paper presents the design and implementation of COVID-Bot, an open-source robotic platform for sanitizing single plant environments such as offices, houses, apartments, among others. This development seeks to create a tool that contributes to the global fight against the COVID-19 pandemic, from a low-cost and easy-to-replicate robot, which disinfects surfaces through type C ultraviolet radiation. The platform is based on a differential robotic base, an RGB-D camera, a tracking camera, three UV-C lamps, and an embedded computer running the ROS-based control software. In addition, this paper presents the description of the hardware used, the software implemented, and the tests carried out to corroborate the operation of the integrated system. These tests demonstrated that the system is adequate to autonomously cover a one-floor apartment, based on the theoretical radiation distance of the used lamps.