Photo de couverture du profil
Vous suivez désormais
Erreur de suivi de l'utilisateur.
Cet utilisateur n'utilise pas les utilisateurs à le suivre.
Vous suivez déjà cet utilisateur.
Votre plan d'adhésion ne permet que 0 suivis. Améliorez ici.
Ne suit désormais plus
Erreur lors de l'arrêt du suivi de l'utilisateur.
Vous avez désormais recommandé
Erreur lors de la recommendation de l'utilisateur.
Une erreur a eu lieu. Veuillez rafraîchir la page et réessayer.
E-mail désormais vérifié.
Avatar de l'utilisateur
$50 USD / heure
Drapeau de INDIA
jaipur, india
$50 USD / heure
Il est actuellement 6:10 PM ici
Rejoint le décembre 1, 2023
0 Recommandations

Bharat S.

@bharatsingh1942

0,0 (0 commentaires)
0,0
0,0
0%
0%
$50 USD / heure
Drapeau de INDIA
jaipur, india
$50 USD / heure
N/A
Travaux complétés
N/A
Suivant le budget
N/A
Dans les temps
N/A
Taux de réembauche

Robotics and AI development

During my Ph.D. journey, I gained invaluable experience in developing a learning framework for Biped Robots and successfully implementing it on real hardware. In this work, I have focused on developing a Learning Framework for Biped robot locomotion over multiple inclines and speeds. Primarily, the framework has two major components: (a) the Gait Model: which provides the joint angles simultaneously to all robot joints, and (b) the State-feedback Mechanism: which provides the feedback signal to the Gait model. In addition, my expertise extends to working with machine learning, deep learning, python programming, embedded systems, inverted pendulums, magnetic levitation systems, single-sided copters, and various inertial measurement units and force-sensitive resistor sensors. Such practical experience, coupled with a strong theoretical foundation in robotics, has equipped me with the skills necessary to make valuable contributions. Therefore, I am trained for the required skill for the solution of problems and development of new things. Please don’t hesitate to reach out if you have any questions regarding my background. I look forward to the opportunity to speak with you .

Contactez Bharat S. concernant votre travail

Connectez-vous pour discuter de tous les détails via la messagerie.

Commentaires

Modifications enregistrées
Aucun commentaire visible ici !

Expérience

Assistant Professor

LNMIIT
août 2023 - Jusqu'à présent
Teaching the Robotics and developing the hardware electrical technology lab.

Éducation

Ph.D.

Malaviya National Institute of Technology, India 2019 - 2023
(4 ans)

Qualifications

Ph.D.

MNIT jaipur
2019
Development of Learning Framework for BIPED robot locomotion control using learning framework.

Publications

Data-driven gait model for bipedal locomotion over continuous changing speeds and inclines

Autonomous Robots
this paper proposes a data-driven Gait model that can handle continuously changing conditions. Data-driven approaches are used to incorporate the joint relationships. Therefore, the deep learning methods are employed to develop seven different data-driven models, namely DNN, LSTM, GRU, BiLSTM, BiGRU, LSTM+GRU, and BiLSTM+BiGRU. The dataset used for training the Gait model consists of walking data from 10 able subjects on continuously changing inclines and speeds.

Universal activation function for data-driven gait model

International Journal of Modelling, Identification and Control
This research work has proposed the universal activation function for the kinematic modelling which is adaptive in sense of application. Twenty-five different activation functions from the literature are compared with the presented activation function in term of mean and maximum model prediction error along the gait trajectory. It shows that the universal activation function-based gait model outperforms others by large margins.

sEMG-based deep learning framework for the automatic detection of knee abnormality

Signal, Image and Video Processing
This paper aims to provide an automated system for the diagnosis of knee abnormality. At first, wavelet denoising was implemented to denoise the sEMG signals. Further, the overlapping windowing method with a window size of 256 ms along with an overlapping of 25% was utilized to minimize the computational complexity. A convolutional neural network (CNN) is used for temporal learning, while long short-term memory (LSTM) is for sequence learning.

Analyzing the impact of activation functions on the performance of the data-driven gait model

Results in Engineering
this research work focuses on the suitability of the activation function for a data-driven gait model for multiple slopes and inclines as ground conditions. Twenty-five activation function with their time complexity is extensively studied. In addition, the fusion of standard error from the subject mean trajectory with conventional loss function is also presented.

Kinematic modeling for biped robot gait trajectory using machine learning techniques

Journal of Bionic Engineering
The MNIT gait dataset consists of walking data on a plane surface of 120 human subjects from different age groups and genders. Thirty-two machine learning models (linear, support vector, k-nearest neighbor, ensemble, probabilistic, and deep learning) trained using the collected dataset. In addition, two types of mapping, (a) one-to-one and (b) many-to-one, are presented for each model.

Reinforcement learning in robotic applications: a comprehensive survey

Artificial Intelligence Review
In this paper, a brief overview of the application of reinforcement algorithms in robotic science is presented. This survey offered a comprehensive review based on segments as (1) development of RL (2) types of RL algorithm like; Actor-Critic, DeepRL, multi-agent RL and Human-centered algorithm (3) various applications of RL in robotics based on their usage platforms such as land-based, water-based and air-based, (4) RL algorithms/mechanism used in robotic applications.

Indirect Force Measurement via Hamiltonian Monte Carlo based Probabilistic Model of FSR Sensor

IEEE Sensors Journal
A Gaussian Process Regressor (GPR) based probabilistic model via the Hamiltonian Monte Carlo (HMC) called GPMC is proposed for capturing the dynamics of FSRs. To demonstrate the uncertainty in force measurement, a 95% prediction interval is drawn for the developed models. The experimental analysis advent that the presented model for the force measurement outperforms other state-of-art methods in terms of mean squared error (MSE), mean absolute error (MAE), and root mean square error (RMSE).

Contactez Bharat S. concernant votre travail

Connectez-vous pour discuter de tous les détails via la messagerie.

Vérifications

Freelance préféré
Identité vérifiée
Paiement vérifié
Téléphone vérifié
E-mail vérifié
Connecté à Facebook
Utilisateur précédent Utilisateur suivant
Invitation désormais envoyée !
Merci ! Nous vous avons envoyé un lien par e-mail afin de réclamer votre crédit gratuit.
Une erreur a eu lieu lors de l'envoi de votre e-mail. Veuillez réessayer.
Utilisateurs enregistrés Total des travaux publiés
Freelancer ® is a registered Trademark of Freelancer Technology Pty Limited (ACN 142 189 759)
Copyright © 2024 Freelancer Technology Pty Limited (ACN 142 189 759)
Chargement de l'aperçu
Permission donnée pour la géolocalisation.
Votre session de connexion a expiré et vous avez été déconnecté. Veuillez vous connecter à nouveau.