A globally converging algorithm for adaptive manipulation and trajectory following for mobile robots with serial redundant arms

Robotica ◽  
2013 ◽  
Vol 31 (8) ◽  
pp. 1299-1311 ◽  
Author(s):  
Paul Moubarak ◽  
Pinhas Ben-Tzvi
Keyword(s):  
Mobile Robots ◽  
Real Time ◽  
A Priori ◽  
Global Optimum ◽  
Search Algorithms ◽  
Initial Guess ◽  
Training Data ◽  
Redundancy Resolution ◽  
Serial Manipulators ◽  
Trajectory Following

SUMMARYIn this paper the tip-over stability of mobile robots during manipulation with redundant arms is investigated in real-time. A new fast-converging algorithm, called the Circles Of INitialization (COIN), is proposed to calculate globally optimal postures of redundant serial manipulators. The algorithm is capable of trajectory following, redundancy resolution, and tip-over prevention for mobile robots during eccentric manipulation tasks. The proposed algorithm employs a priori training data generated from an exhaustive resolution of the arm's redundancy along a single direction in the manipulator's workspace. This data is shown to provide educated initial guess that enables COIN to swiftly converge to the global optimum for any other task in the workspace. Simulations demonstrate the capabilities of COIN, and further highlight its convergence speed relative to existing global search algorithms.

A Real-Time-Capable Closed-Form Multi-Objective Redundancy Resolution Scheme for Seven-DoF Serial Manipulators

2021 ◽  
Vol 6 (2) ◽  
pp. 431-438
Author(s):  
Wolfgang Wiedmeyer ◽  
Philipp Altoe ◽  
Jonathan Auberle ◽  
Christoph Ledermann ◽  
Torsten Kroger
Keyword(s):  
Closed Form ◽  
Real Time ◽  
Redundancy Resolution ◽  
Serial Manipulators ◽  
Multi Objective ◽  
Resolution Scheme

scholarly journals Robust Approach to Supervised Deep Neural Network Training for Real-Time Object Classification in Cluttered Indoor Environment

2021 ◽  
Vol 11 (15) ◽  
pp. 7148
Author(s):  
Bedada Endale ◽  
Abera Tullu ◽  
Hayoung Shi ◽  
Beom-Soo Kang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Real Time ◽  
Network Architecture ◽  
Input Data ◽  
Deep Neural Network ◽  
Data Augmentation ◽  
Object Classification ◽  
Training Data ◽  
Gradient Descent Algorithm

Unmanned aerial vehicles (UAVs) are being widely utilized for various missions: in both civilian and military sectors. Many of these missions demand UAVs to acquire artificial intelligence about the environments they are navigating in. This perception can be realized by training a computing machine to classify objects in the environment. One of the well known machine training approaches is supervised deep learning, which enables a machine to classify objects. However, supervised deep learning comes with huge sacrifice in terms of time and computational resources. Collecting big input data, pre-training processes, such as labeling training data, and the need for a high performance computer for training are some of the challenges that supervised deep learning poses. To address these setbacks, this study proposes mission specific input data augmentation techniques and the design of light-weight deep neural network architecture that is capable of real-time object classification. Semi-direct visual odometry (SVO) data of augmented images are used to train the network for object classification. Ten classes of 10,000 different images in each class were used as input data where 80% were for training the network and the remaining 20% were used for network validation. For the optimization of the designed deep neural network, a sequential gradient descent algorithm was implemented. This algorithm has the advantage of handling redundancy in the data more efficiently than other algorithms.

MobileNet-Yolo Based wildlife detection model: A case study in yunnan tongbiguan nature reserve, China

2021 ◽  
pp. 1-11
Author(s):  
Tingting Zhao ◽  
Xiaoli Yi ◽  
Zhiyong Zeng ◽  
Tao Feng
Keyword(s):  
Real Time ◽  
Nature Reserve ◽  
Complex Model ◽  
Training Data ◽  
Mean Average Precision ◽  
Detection Accuracy ◽  
High Definition ◽  
Average Precision ◽  
Data Set ◽  
Real Time Detection

YTNR (Yunnan Tongbiguan Nature Reserve) is located in the westernmost part of China’s tropical regions and is the only area in China with the tropical biota of the Irrawaddy River system. The reserve has abundant tropical flora and fauna resources. In order to realize the real-time detection of wild animals in this area, this paper proposes an improved YOLO (You only look once) network. The original YOLO model can achieve higher detection accuracy, but due to the complex model structure, it cannot achieve a faster detection speed on the CPU detection platform. Therefore, the lightweight network MobileNet is introduced to replace the backbone feature extraction network in YOLO, which realizes real-time detection on the CPU platform. In response to the difficulty in collecting wild animal image data, the research team deployed 50 high-definition cameras in the study area and conducted continuous observations for more than 1,000 hours. In the end, this research uses 1410 images of wildlife collected in the field and 1577 wildlife images from the internet to construct a research data set combined with the manual annotation of domain experts. At the same time, transfer learning is introduced to solve the problem of insufficient training data and the network is difficult to fit. The experimental results show that our model trained on a training set containing 2419 animal images has a mean average precision of 93.6% and an FPS (Frame Per Second) of 3.8 under the CPU. Compared with YOLO, the mean average precision is increased by 7.7%, and the FPS value is increased by 3.

Klasifikasi Gerakan Jatuh Berbasis Accelerometer dan Gyroscope Menggunakan K-Nearest Neighbors

2020 ◽  
Vol 4 (2) ◽  
pp. 24-29
Author(s):  
Adlian Jefiza ◽  
Indra Daulay ◽  
Jhon Hericson Purba
Keyword(s):  
Real Time ◽  
Root Mean Square ◽  
Nearest Neighbors ◽  
Training Data ◽  
Mean Square ◽  
K Nearest Neighbors ◽  
Testing Data ◽  
Total Data

Permasalahan utama pada penelitian ini merujuk kepada semakin menurunnya daya tahan tubuh lanjut usia (lansia). Hal ini membutuhkan sistem monitoring aktivitas lansia secara real time. Untuk mendeteksi kegiatan para lansia, dirancang sebuah perangkat monitoring dengan accelerometer 3-sumbu dan gyroscope 3-sumbu. Data sensor diperoleh dari lima partisipan. Setiap partisipan melakukan lima gerakan yaitu terjatuh, duduk, tidur, rukuk dan sujud. Gerakan yang dipilih adalah gerakan yang menyerupai gerakan jatuh. Total data yang diperoleh dari partisipan adalah 75 data yang terbagi menjadi training data dan testing data. Penelitian ini menggunakan metode transformasi Wavelet untuk mengenali fitur dari gerakan. Untuk pengklasifikasian setiap gerakan, digunakan metode K-nearest neighbors (KNN). Hasil klasifikasi gerakan menggunakan lima kelas menghasilkan nilai root mean square sebesar 0.0074 dengan akurasi 100%.

Bio-Inspired, Real-Time Passive Vision for Mobile Robots

2019 ◽  
pp. 33-58
Author(s):  
Piotr Skrzypczyński ◽  
Marta Rostkowska ◽  
Marek Wa̧sik
Keyword(s):  
Mobile Robots ◽  
Real Time

scholarly journals Utilisation of CryoSat-2 SAR altimeter in operational ice charting

2016 ◽  
Vol 10 (1) ◽  
pp. 121-131 ◽  
Author(s):  
E. Rinne ◽  
M. Similä
Keyword(s):  
Synthetic Aperture Radar ◽  
Real Time ◽  
Training Data ◽  
Synthetic Aperture ◽  
First Year ◽  
Success Rates ◽  
Hit Rate ◽  
Snow Conditions ◽  
Simple Product ◽  
Barents And Kara Seas

Abstract. We present methods to utilise CryoSat-2 (CS-2) synthetic aperture radar (SAR) mode data in operational ice charting. We compare CS-2 data qualitatively to SAR mosaics over the Barents and Kara seas. Furthermore, we compare the CS-2 to archived operational ice charts. We present distributions of four CS-2 waveform parameters for different ice types as presented in the ice charts. We go on to present an automatic classification method for CS-2 data which, after training with operational ice charts, is capable of determining open ocean from ice with a hit rate of  >  90 %. The training data are dynamically updated every 5 days using the most recent 15 days of CS-2 data and operative ice charts. This helps the adaption of the classifier to the evolving ice/snow conditions throughout winter. The classifier is also capable of detecting three different ice classes (thin and thick first-year ice as well as old ice) with success rates good enough for the output to be usable to support operational ice charting. Finally, we present a near-real-time CS-2 product just plotting the waveform characteristics and conclude that even such a simple product is usable for some of the needs of ice charting.

Sign in / Sign up

Export Citation Format

Share Document