In this work, the transfer learning paradigm is used to improve the performance of neural networks. These networks estimate the collision point between the robot and an external object, using two different approaches....
详细信息
The paper is focused on the problem of the stiffness model estimation that could be used in combination with double encoders for the detection of the compliance errors and applied forces. Algebraic approach is propose...
详细信息
This paper is focused on a problem of using reaction predictors in the control pipeline of walking robots. The use of such predictors has been proposed for bipedal robots and the main advantage of this proposal is tha...
详细信息
The robot's Jacobian is an important tool since it allows to solve different problems, from calculating the trajectory of motion to modeling dynamics in task space. Here we demonstrate the algorithm that allows ca...
详细信息
In this paper we present a technique for finding periodic gaits for five-link planar bipedal robot with point feet. Unlike most works that are limited to the consideration of only underactuated single support phase (S...
详细信息
Modern robotics represents a collaboration between industry and scientific community, with interdisciplinary research being at its forefront. This leads to wide variation in the requirements for robotic systems, which...
详细信息
This paper is focused on control of variable stiffness actuators (VSA). One of the new approaches in this area is based on a linear VSA model, whose main features are the directly controlled linear stiffness dynamics ...
详细信息
The reinforcement learning approach allows learning desired control policy in different environments without explicitly providing system dynamics. A model-free deep Q-learning algorithm is proven to be efficient on a ...
详细信息
Self-driving vehicles contain a number of modules allowing them to autonomously navigate in uncertain environment. The robust, efficient, safe and accurate autonomous navigation are heavily depend on parameters of a p...
详细信息
The study is focused on velocity control of a manipulator motion in the case when the precise execution of commands cannot be guaranteed because of the imperfection of the control system or interaction with the robot ...
详细信息
暂无评论