Predrag Milosavljevic

Learn More
Anthropomimetic robotics differs from conventional approaches by capitalizing on the replication of the inner structures of the human body, such as muscles, tendons, bones, and joints. Here we present our results of more than three years of research in constructing, simulating, and, most importantly, controlling anthropomimetic robots. We manufactured four(More)
Copying human physiology leads us to the first truly anthropomimetic robot-ECCEROBOT, driven by the antagonistically coupled compliant drives. Control design of such a mechanism appears as a really demanding and challenging mission. Puller-follower concept, developed for the robotic joint with antagonistically coupled drives, is expanded to the multi-joint(More)
This paper presents a wheeled humanoid robot as a structure composed by upper human-like body and mobile platform. The cart construction is supported by two driving wheels and one caster wheel and subjected to nonholonomic kinematic constraints. The real system configuration of the upper body and its model are represented as a fully anthropomimetic,(More)
We discuss optimal load sharing of parallel gas compressors in the presence of plant-model mismatch. We formulate this problem as a static real-time optimization task and propose to tackle it by means of modifier adaptation. Under mild assumptions, the chosen approach guarantees optimal operating conditions upon convergence. Furthermore, we discuss how the(More)
The desire to operate chemical processes in a safe and economically optimal way has motivated the development of so-called real-time optimization (RTO) methods [1]. For continuous processes, these methods aim to compute safe and optimal steady-state setpoints for the lower-level process controllers. A key challenge for this task is plant-model mismatch. For(More)
The paper deals with a rapidly growing trend in robotics - anthropomimetics. Following a human paragon, bio-inspired control of the robot arm is presented using artificial neural networks. This work demonstrates results achieved by feedforward control comparing feedforward backpropagation networks and radial bases networks. Use of radial bases network(More)
  • 1