Robots that can easily interact with humans and move through natural environments are becoming increasingly essential as assistive devices in the home, office and hospital. These machines need to be safe, effective, and easy to control. One strategy ...
In many application domains, conventional e-noses are frequently outperformed in both speed and accuracy by their biological counterparts. Exploring potential bio-inspired improvements, we note a number of neuronal network models have demonstrated so...
Robotic researchers have been greatly inspired by the human hand in the search to design and build adaptive robotic hands. Especially, joints have received a lot of attention upon their role in maintaining the passive compliance that gives the finger...
Recent advances in understanding fish locomotion with robotic devices have included the use of biomimetic flapping based and fin undulatory locomotion based robots, treating two locomotions separately from each other. However, in most fish species, p...
Animal-Robot Interaction experiments have demonstrated their usefulness to understand the social behaviour of a growing number of animal species. In order to study the mechanisms of social influences (from parents and peers) on behavioural developmen...
The energy consumption of worm robots is composed of three parts: heat losses in the motors, internal friction losses of the worm device and mechanical energy locomotion requirements which we refer to as the cost of transport (COT). The COT, which is...
Several robotics applications require high torque-to-weight ratio and energy efficient actuators. Progress in that direction was made by introducing compliant elements into the actuation. A large variety of actuators were developed such as series ela...
In recent years, simple biomimetic robots have been increasingly used in biological studies to investigate social behavior, for example collective movement. Nevertheless, a big challenge in developing biomimetic robots is the acceptance of the roboti...
The autoencoder algorithm is a simple but powerful unsupervised method for training neural networks. Autoencoder networks can learn sparse distributed codes similar to those seen in cortical sensory areas such as visual area V1, but they can also be ...
Join thousands of healthcare professionals staying informed about the latest AI breakthroughs in medicine. Get curated insights delivered to your inbox.