Abstract
One of the essential attributes of a cleaning robot is to achieve complete area coverage. Current commercial indoor cleaning robots have fixed morphology and are restricted to clean only specific areas in a house. The results of maximum area coverage are sub-optimal in this case. Tiling robots are innovative solutions for such a coverage problem. These new kinds of robots can be deployed in the cases of cleaning, painting, maintenance, and inspection, which require complete area coverage. Tiling robots’ objective is to cover the entire area by reconfiguring to different shapes as per the area requirements. In this context, it is vital to have a framework that enables the robot to maximize the area coverage while minimizing energy consumption. That means it is necessary for the robot to cover the maximum area with the least number of shape reconfigurations possible. The current paper proposes a complete area coverage planning module for the modified hTrihex, a honeycomb-shaped tiling robot, based on the deep reinforcement learning technique. This framework simultaneously generates the tiling shapes and the trajectory with minimum overall cost. In this regard, a convolutional neural network (CNN) with long short term memory (LSTM) layer was trained using the actor-critic experience replay (ACER) reinforcement learning algorithm. The simulation results obtained from the current implementation were compared against the results that were generated through traditional tiling theory models that included zigzag, spiral, and greedy search schemes. The model presented in the current paper was also compared against other methods where this problem was considered as a traveling salesman problem (TSP) solved through genetic algorithm (GA) and ant colony optimization (ACO) approaches. Our proposed scheme generates a path with a minimized cost at a lesser time.
Highlights
Cleaning has always been an important activity to humans
There is a need for robots that can change shape to access tight spaces based on the layout, and that is where reconfigurable tiling robots come into the picture
The path planning attempt for the modified hTrihex robot is modelled as a Markov decision process (MDP)
Summary
Commercial autonomous cleaning devices for houses have seen a rise over the past few years. Even though they are commercially successful, their fixed morphology hinders them from reaching their maximum cleaning capacity. The commonly available commercial cleaning robots are round in shape, and this fixed shape cannot allow them to reach tight spaces under an indoor setting. This impacts the area coverage which is a crucial factor for cleaning robots. The ability to change their morphology helps them to achieve this objective
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have