Visual Rewards From Observation for Sequential Tasks: Autonomous Pile Loading.

One of the key challenges in implementing reinforcement learning methods for real-world robotic applications is the design of a suitable reward function. In field robotics, the absence of abundant datasets, limited training time, and high variation of environmental conditions complicate the task further. In this paper, we review reward learning techniques together with visual representations commonly used in current state-of-the-art works in robotics.

Design and application of a fish-shaped lateral line probe for flow measurement.

We introduce the lateral line probe (LLP) as a measurement device for natural flows. Hydraulic surveys in rivers and hydraulic structures are currently based on time-averaged velocity measurements using propellers or acoustic Doppler devices. The long-term goal is thus to develop a sensor system, which includes spatial gradients of the flow field along a fish-shaped sensor body.