This work proposes a hybrid control methodology to achieve full body collision avoidance in anthropomorphic robot manipulators. The proposal improves classical motion planning algorithms by introducing a Deep Reinforcement Learning (DRL) approach trained ad hoc for performing obstacle avoidance, while achieving a reaching task in the operative space. More specifically, a switching mechanism is enabled whenever a condition of proximity to the obstacles is met, thus conferring to the dualmode architecture a self-configuring capability in order to cope with objects unexpectedly invading the workspace. The proposal has been finally tested relying on a realistic robot manipulator simulated in a V-REP environment.
In this paper a real-time collision avoidance approach using machine learning is presented for safe humanrobot coexistence. More specifically, the collision avoidance problem is tackled with Deep Reinforcement Learning (DRL) techniques, applied to robot manipulators with a workspace invaded by unpredictable obstacles. Since the robotic systems are defined in the continuous space, a Normalized Advantage Function (NAF) model-free algorithm has been used. In order to assess the proposal, a robotic system, that is a COMAU-SMART3-S2 anthropomorphic robot manipulator, has been considered. The robotic system has been interfaced with external tools for evaluation, control, and automatic training. Simulations carried out on a virtual environment are finally reported to show the effectiveness of the proposed model-free deep reinforcement learning algorithm.
This paper deals with the design of a switching control scheme for robot manipulators. The key elements of the proposed scheme are the inverse dynamics based centralized controller and a set of decentralized controllers. They enable to realize two possible control structures: one of centralized type, the other of decentralized type. All the controllers are based on Integral Sliding Mode (ISM), so that matched disturbances and uncertain terms, due to unmodeled dynamics or couplings effects, are suitably compensated. The idea of using ISM, apart from its feature of providing robustness in front of a wide class of uncertainties, is motivated by its capability of acting as a "perturbation estimator", which is a clear advantage in the considered case. In fact, it allows one to define a switching rule in order to choose one of the two control structures featured in the scheme, depending on the requested performances. As a consequence, the resulting control scheme is more efficient from computational viewpoint, while maintaining the advantages in terms of stability and robustness of the conventional standalone control schemes. In addition, the scheme can accommodate a variety of velocity and acceleration requirements, in contrast with the capability of the genuine decentralized or centralized control structures. The verification and the validation of our proposal have been carried out in simulation, relying on a model of an industrial robot manipulator COMAU SMART3-S2, with injected noise to better emulate a realistic setup.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.