Online Terrain Classification Using Neural Network for Disaster Robot Application

Sanusi, Muhammad Anwar; Dewantara, Bima Sena Bayu; Setiawardhana,; Sigit, Riyanto

doi:10.33022/ijcs.v12i1.3132

Cited by 3 publications

(6 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An artificial neural network (ANN) was applied for the terrain classification in the research presented in [37]. The ANN was implemented on the Raspberry Pi 4B in order to process the vibration data in real time.…”

Section: Classification Methods For Terrain Type Recognitionmentioning

confidence: 99%

A Survey of Machine Learning Approaches for Mobile Robot Control

Rybczak,

Popowniak,

Lazarowska

2024

Robotics

View full text Add to dashboard Cite

Machine learning (ML) is a branch of artificial intelligence that has been developing at a dynamic pace in recent years. ML is also linked with Big Data, which are huge datasets that need special tools and approaches to process them. ML algorithms make use of data to learn how to perform specific tasks or make appropriate decisions. This paper presents a comprehensive survey of recent ML approaches that have been applied to the task of mobile robot control, and they are divided into the following: supervised learning, unsupervised learning, and reinforcement learning. The distinction of ML methods applied to wheeled mobile robots and to walking robots is also presented in the paper. The strengths and weaknesses of the compared methods are formulated, and future prospects are proposed. The results of the carried out literature review enable one to state the ML methods that have been applied to different tasks, such as the following: position estimation, environment mapping, SLAM, terrain classification, obstacle avoidance, path following, learning to walk, and multirobot coordination. The survey allowed us to associate the most commonly used ML algorithms with mobile robotic tasks. There still exist many open questions and challenges such as the following: complex ML algorithms and limited computational resources on board a mobile robot; decision making and motion control in real time; the adaptability of the algorithms to changing environments; the acquisition of large volumes of valuable data; and the assurance of safety and reliability of a robot’s operation. The development of ML algorithms for nature-inspired walking robots also seems to be a challenging research issue as there exists a very limited amount of such solutions in the recent literature.

show abstract

Section: Classification Methods For Terrain Type Recognitionmentioning

confidence: 99%

A Survey of Machine Learning Approaches for Mobile Robot Control

Rybczak,

Popowniak,

Lazarowska

2024

Robotics

View full text Add to dashboard Cite

show abstract

“…This research results in the production of two distinct types of robots that are supplied with a variety of mechanisms. One example is the unmanned ground vehicle (UGV), which is outfitted with a variety of mechanisms for walking to identify things, arm mechanisms, and sensory capabilities that are utilized for the purposes of observation and exploration [20], [25], [26].…”

Section: Methodsmentioning

confidence: 99%

“…Exploration and observation are two of the most common uses for unmanned ground vehicles (UGV), which are purpose-built to have good ground roaming capabilities [19]. After then, UAVs are utilized for air exploration missions in a more general sense for the goals of mapping and exploration by air [20].…”

Section: Introductionmentioning

confidence: 99%

Environmental Monitoring System using Wireless Multi-Node Sensors based Communication System on Volcano Observations Drones

Huda,

Setiawardhana,

Dewantara

et al. 2024

JOIV : Int. J. Inform. Visualization

View full text Add to dashboard Cite

Indonesia is on the Ring of Fire and has the world's most active volcanoes. Volcanic activity has a significant effect on the landscape and on the people who live there. The difficulty of evacuating and helping victims requires hard work and sometimes even the safety of the rescue team itself. For this reason, high-tech tools are needed. Unmanned aerial vehicles (UAVs), also called drones, have become a hopeful tool for remote environmental monitoring in recent years. The system design has a monitoring platform, gateway, and sensor nodes attached to the UAV, which monitors the content of toxic gas contamination in the air. Using IoT technology, sensor data is sent wirelessly to a central monitoring station for a thorough and accurate volcanic activity study. This system is a flexible and complete way to monitor volcanic activity, learn more about it, and make it easier to respond to disasters. Tests are also done to measure system speed, including latency, and determine network service quality. The results show that data is successfully sent in real-time from the sensor nodes to the monitoring system. The average Round-Trip time for the payload transmission is 446.046226 ms. This shows how well the system works to send data from the sensors connected to the UAV to the monitoring station. The UAV has sensor nodes and a monitoring system platform. These can be used to build and optimize disaster mitigation systems.

show abstract

“…Gyroscopes, which measure angular velocity around one or more axes, are widely used in pattern recognition applications, such as human movement or activity recognition [32,33]. In terrain classification tasks, these sensors were mainly tested together with accelerometers [31,[34][35][36][37][38]. In a previous study, the authors of this paper showed that gyroscopes can provide significantly higher classification efficiencies than accelerometers using a frequency domain-based feature set [39].…”

Section: Introductionmentioning

confidence: 98%

“…Hasan et al applied altogether 60 different temporal, statistical and spectral features using accelerometer and gyroscope data together to classify 9 indoor surface types [37]. In [38], the components of the amplitude spectrum computed for the six channels of the IMU sensor were used together as inputs of the ANN to classify terrains into five classes, i.e., indoor floor, asphalt, grass, soil, and loose gravel.…”

Section: Introductionmentioning

confidence: 99%

Online Outdoor Terrain Classification Algorithm for Wheeled Mobile Robots Equipped with Inertial and Magnetic Sensors

et al. 2023

View full text Add to dashboard Cite

Terrain classification provides valuable information for both control and navigation algorithms of wheeled mobile robots. In this paper, a novel online outdoor terrain classification algorithm is proposed for wheeled mobile robots. The algorithm is based on only time-domain features with both low computational and low memory requirements, which are extracted from the inertial and magnetic sensor signals. Multilayer perceptron (MLP) neural networks are applied as classifiers. The algorithm is tested on a measurement database collected using a prototype measurement system for various outdoor terrain types. Different datasets were constructed based on various setups of processing window sizes, used sensor types, and robot speeds. To examine the possibilities of the three applied sensor types in the application, the features extracted from the measurement data of the different sensors were tested alone, in pairs and fused together. The algorithm is suitable to operate online on the embedded system of the mobile robot. The achieved results show that using the applied time-domain feature set the highest classification efficiencies on unknown data can be above 98%. It is also shown that the gyroscope provides higher classification rates than the widely used accelerometer. The magnetic sensor alone cannot be effectively used but fusing the data of this sensor with the data of the inertial sensors can improve the performance.

show abstract

Online Terrain Classification Using Neural Network for Disaster Robot Application

Cited by 3 publications

References 1 publication

A Survey of Machine Learning Approaches for Mobile Robot Control

A Survey of Machine Learning Approaches for Mobile Robot Control

Environmental Monitoring System using Wireless Multi-Node Sensors based Communication System on Volcano Observations Drones

Online Outdoor Terrain Classification Algorithm for Wheeled Mobile Robots Equipped with Inertial and Magnetic Sensors

Contact Info

Product

Resources

About