CircuitBot: Learning to survive with robotic circuit drawing.

Robots with the ability to actively acquire power from surroundings will be greatly beneficial for long-term autonomy and to survive in uncertain environments. In this work, a scenario is presented where a robot has limited energy, and the only way to survive is to access the energy from an unregulated power source. With no wires or resistors available, the robot heuristically learns to maximize the input voltage on its system while avoiding potential obstacles during the connection.

Variable Stiffness Object Recognition with a CNN-Bayes Classifier on a Soft Gripper.

Soft grippers significantly widen the palpation capabilities of robots, ranging from soft to hard materials without the assistance of cameras. From a medical perspective, the detection of size and shape of hard inclusions concealed within soft three-dimensional (3D) objects is meaningful for the early detection of cancer through palpation. This article proposes a framework for variable-stiffness object recognition using tactile information collected by force sensitive resistors on a three-finger soft gripper.

Bootstrapping Virtual Bipedal Walkers with Robotics Scaffolded Learning.

We reach walking optimality from a very early age by using natural supports, which can be the hands of our parents, chairs, and training wheels, and bootstrap a new knowledge from the recently acquired one. The idea behind bootstrapping is to use the previously acquired knowledge from simpler tasks to accelerate the learning of more complicated ones. In this paper, we propose a scaffolded learning method from an evolutionary perspective, where a biped creature achieves stable and independent bipedal walking while exploiting the natural scaffold of its changing morphology to create a third limb.

Simulating the evolution of bipedalism and the absence of static bipedal hexapods.

In nature, very few animals locomote on two legs. Static bipedalism can be found in four limbed and five limbed animals like dogs, cats, birds, monkeys and kangaroos, but it cannot be seen in hexapods or other multi-limbed animals. In this paper, we present a simulation with a novel perspective on the evolution of static bipedalism, with a virtual creature evolving its body and controllers, and we apply an evolutionary algorithm to explore the locomotion transition from octapods to bipods.

Risk-Aware Model-Based Control.

Model-Based Reinforcement Learning (MBRL) algorithms have been shown to have an advantage on data-efficiency, but often overshadowed by state-of-the-art model-free methods in performance, especially when facing high-dimensional and complex problems. In this work, a novel MBRL method is proposed, called Risk-Aware Model-Based Control (RAMCO). It combines uncertainty-aware deep dynamics models and the risk assessment technique Conditional Value at Risk (CVaR).

Robotic investigation on effect of stretch reflex and crossed inhibitory response on bipedal hopping.

To maintain balance during dynamic locomotion, the effects of proprioceptive sensory feedback control (e.g. reflexive control) should not be ignored because of its simple sensation and fast reaction time.

The trade-off between morphology and control in the co-optimized design of robots.

Conventionally, robot morphologies are developed through simulations and calculations, and different control methods are applied afterwards. Assuming that simulations and predictions are simplified representations of our reality, how sure can roboticists be that the chosen morphology is the most adequate for the possible control choices in the real-world? Here we study the influence of the design parameters in the creation of a robot with a Bayesian morphology-control (MC) co-optimization process. A robot autonomously creates child robots from a set of possible design parameters and uses Bayesian Optimization (BO) to infer the best locomotion behavior from real world experiments.

Embroidered archimedean spiral electrodes for contactless prosthetic control.

With continuous advancements on active prosthetics the detection of the user's intention becomes the new technological bottleneck. While electromyography (EMG) is widely used to detect individual muscular contributions, sweat and relative sensor movements degrade the quality of the signal over time. In this paper, we bypass the problems created with the skin contact analyzing the muscular activation with Archimedean Spiral (AS) electrodes.

Evolutionary Developmental Robotics: Improving Morphology and Control of Physical Robots.

Evolutionary algorithms have previously been applied to the design of morphology and control of robots. The design space for such tasks can be very complex, which can prevent evolution from efficiently discovering fit solutions. In this article we introduce an evolutionary-developmental (evo-devo) experiment with real-world robots.

Energy efficient hopping with Hill-type muscle properties on segmented legs.

The intrinsic muscular properties of biological muscles are the main source of stabilization during locomotion, and superior biological performance is obtained with low energy costs. Man-made actuators struggle to reach the same energy efficiency seen in biological muscles. Here, we compare muscle properties within a one-dimensional and a two-segmented hopping leg.

Stretch reflex improves rolling stability during hopping of a decerebrate biped system.

When humans hop, attitude recovery can be observed in both the sagittal and frontal planes. While it is agreed that the brain plays an important role in leg placement, the role of low-level feedback (the stretch reflex) on frontal plane stabilization remains unclear. Seeking to better understand the contribution of the soleus stretch reflex to rolling stability, we performed experiments on a biomimetic humanoid hopping robot.