Goto

Collaborating Authors

Towards Safe Control of Continuum Manipulator Using Shielded Multiagent Reinforcement Learning

arXiv.org Artificial Intelligence

Continuum robotic manipulators are increasingly adopted in minimal invasive surgery. However, their nonlinear behavior is challenging to model accurately, especially when subject to external interaction, potentially leading to poor control performance. In this letter, we investigate the feasibility of adopting a model-free multiagent reinforcement learning (RL), namely multiagent deep Q network (MADQN), to control a 2-degree of freedom (DoF) cable-driven continuum surgical manipulator. The control of the robot is formulated as a one-DoF, one agent problem in the MADQN framework to improve the learning efficiency. Combined with a shielding scheme that enables dynamic variation of the action set boundary, MADQN leads to efficient and importantly safer control of the robot. Shielded MADQN enabled the robot to perform point and trajectory tracking with submillimeter root mean square errors under external loads, soft obstacles, and rigid collision, which are common interaction scenarios encountered by surgical manipulators. The controller was further proven to be effective in a miniature continuum robot with high structural nonlinearitiy, achieving trajectory tracking with submillimeter accuracy under external payload.


Robots and Artificial Intelligence Vinod Sharma's Blog

@machinelearnbot

Hollywood movies telling us since long those Robots are coming to get us, people were enjoying these indications as jokes and science fiction movies. Some time back New York Times and Mr. Musk told us the same thing but this time we are serious and anxious. In early days if some one answers to our very old-style question "What do you do" regardless of your origin or culture or from you come from or language you speak we get same question very often. If the answer was "I do artificial intelligence" and immediate reaction was "Why don't you have natural one". Today if the answer to the same question is "I do artificial intelligence"; immediate reaction is "Please don't hurt me / us".


Stability Constrained Mobile Manipulation Planning on Rough Terrain

arXiv.org Artificial Intelligence

This paper presents a framework that allows online dynamic-stability-constrained optimal trajectory planning of a mobile manipulator robot working on rough terrain. First, the kinematics model of a mobile manipulator robot, and the Zero Moment Point (ZMP) stability measure are presented as theoretical background. Then, a sampling-based quasi-static planning algorithm modified for stability guarantee and traction optimization in continuous dynamic motion is presented along with a mathematical proof. The robot's quasi-static path is then used as an initial guess to warm-start a nonlinear optimal control solver which may otherwise have difficulties finding a solution to the stability-constrained formulation efficiently. The performance and computational efficiency of the framework are demonstrated through an application to a simulated timber harvesting mobile manipulator machine working on varying terrain. The results demonstrate feasibility of online trajectory planning on varying terrain while satisfying the dynamic stability constraint.


Trump Administration Won't Brand China Currency Manipulator

U.S. News

In a report issued Wednesday, the administration says no country meets the criteria to be labeled a currency manipulator. But the report says that six nations -- China, Germany, India, Japan, South Korea and Switzerland -- will remain on a watch list subjecting them to added U.S. pressure to lower trade surpluses.


Whole-Body Control on Non-holonomic Mobile Manipulation for Grapevine Winter Pruning Automation

arXiv.org Artificial Intelligence

Mobile manipulators that combine mobility and manipulability, are increasingly being used for various unstructured application scenarios in the field, e.g. vineyards. Therefore, the coordinated motion of the mobile base and manipulator is an essential feature of the overall performance. In this paper, we explore a whole-body motion controller of a robot which is composed of a 2-DoFs non-holonomic wheeled mobile base with a 7-DoFs manipulator (non-holonomic wheeled mobile manipulator, NWMM) This robotic platform is designed to efficiently undertake complex grapevine pruning tasks. In the control framework, a task priority coordinated motion of the NWMM is guaranteed. Lower-priority tasks are projected into the null space of the top-priority tasks so that higher-priority tasks are completed without interruption from lower-priority tasks. The proposed controller was evaluated in a grapevine spur pruning experiment scenario.