scholarly journals Pick and Place Operations in Logistics Using a Mobile Manipulator Controlled with Deep Reinforcement Learning

2019 ◽  
Vol 9 (2) ◽  
pp. 348 ◽  
Author(s):  
Ander Iriondo ◽  
Elena Lazkano ◽  
Loreto Susperregi ◽  
Julen Urain ◽  
Ane Fernandez ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Path Planning ◽  
Mobile Manipulator ◽  
Complex Tasks ◽  
Complex Control ◽  
Planning And Control ◽  
Pick And Place ◽  
Policy Gradient ◽  
Point To Point ◽  
And Control

Programming robots to perform complex tasks is a very expensive job. Traditional path planning and control are able to generate point to point collision free trajectories, but when the tasks to be performed are complex, traditional planning and control become complex tasks. This study focused on robotic operations in logistics, specifically, on picking objects in unstructured areas using a mobile manipulator configuration. The mobile manipulator has to be able to place its base in a correct place so the arm is able to plan a trajectory up to an object in a table. A deep reinforcement learning (DRL) approach was selected to solve this type of complex control tasks. Using the arm planner’s feedback, a controller for the robot base is learned, which guides the platform to such a place where the arm is able to plan a trajectory up to the object. In addition the performance of two DRL algorithms ((Deep Deterministic Policy Gradient (DDPG)) and (Proximal Policy Optimisation (PPO)) is compared within the context of a concrete robotic task.

Differentially Flat Designs of Mobile Vehicles With Under-Actuated Manipulator Arms

2007 ◽  
Author(s):  
Ji-Chul Ryu ◽  
Vivek Sangwan ◽  
Sunil K. Agrawal
Keyword(s):  
Controller Design ◽  
Mobile Manipulator ◽  
Differential Flatness ◽  
Combined System ◽  
Planning And Control ◽  
Mobile Vehicle ◽  
Highly Nonlinear ◽  
Manipulator Arm ◽  
Point To Point ◽  
And Control

Differential flatness has been investigated in the context of mobile vehicles for planning and control of their motions. In these models, the wheels are considered to be non-slipping, i.e., the system dynamics is subject to non-holonomic constraints. If a manipulator arm is mounted on such a mobile vehicle, the dynamics becomes highly nonlinear due to the nonlinear coupling between the motions of the mobile vehicle and the manipulator arm. A challenging question is how to perform point-to-point motions of such a system in the state space of the mobile manipulator. If some of the actuators are absent in the mechanical arm, the mobile manipulator becomes under-actuated and consequently even harder to plan and control. This paper presents a methodology for design of mobile vehicles, mounted with under-actuated manipulators operating in a horizontal plane, such that the combined system is differentially flat. In this paper, we show that by appropriate inertia distribution of the links and addition of torsion springs at the joints, a range of under-actuated designs are possible where the underactuated mobile manipulator system is differentially flat. The differential flatness property allows to efficiently solve the problem of trajectory planning and feedback controller design for point to point motions of the system. The proposed method is illustrated by the example of a mobile vehicle with under-actuated three-link manipulator.

Reinforcement learning-based radar-evasive path planning: a comparative analysis

2021 ◽  
pp. 1-18
Author(s):  
R.U. Hameed ◽  
A. Maqsood ◽  
A.J. Hashmi ◽  
M.T. Saeed ◽  
R. Riaz
Keyword(s):  
Reinforcement Learning ◽  
Path Planning ◽  
Learning Algorithms ◽  
Optimal Path ◽  
Trust Region ◽  
Optimal Path Planning ◽  
Optimal Paths ◽  
Policy Gradient ◽  
Model Aircraft ◽  
Tracking Model

Abstract This paper discusses the utilisation of deep reinforcement learning algorithms to obtain optimal paths for an aircraft to avoid or minimise radar detection and tracking. A modular approach is adopted to formulate the problem, including the aircraft kinematics model, aircraft radar cross-section model and radar tracking model. A virtual environment is designed for single and multiple radar cases to obtain optimal paths. The optimal trajectories are generated through deep reinforcement learning in this study. Specifically, three algorithms, namely deep deterministic policy gradient, trust region policy optimisation and proximal policy optimisation, are used to find optimal paths for five test cases. The comparison is carried out based on six performance indicators. The investigation proves the importance of these reinforcement learning algorithms in optimal path planning. The results indicate that the proximal policy optimisation approach performed better for optimal paths in general.

Evolutionary Control of Helicopter Hovering Based on Genetic Programming

2013 ◽  
pp. 1-19
Author(s):  
Dimitris C. Dracopoulos ◽  
Dimitrios Effraimidis
Keyword(s):  
Reinforcement Learning ◽  
Genetic Programming ◽  
Control Problems ◽  
Complex Control ◽  
Fuzzy Methods ◽  
Neuro Fuzzy ◽  
Complex Control System ◽  
And Control ◽  
Intelligent Controllers ◽  
Hovering Control

Computational intelligence techniques such as neural networks, fuzzy logic, and hybrid neuroevolutionary and neuro-fuzzy methods have been successfully applied to complex control problems in the last two decades. Genetic programming, a field under the umbrella of evolutionary computation, has not been applied to a sufficiently large number of challenging and difficult control problems, in order to check its viability as a general methodology to such problems. Helicopter hovering control is considered a challenging control problem in the literature and has been included in the set of benchmarks of recent reinforcement learning competitions for deriving new intelligent controllers. This chapter shows how genetic programming can be applied for the derivation of controllers in this nonlinear, high dimensional, complex control system. The evolved controllers are compared with a neuroevolutionary approach that won the first position in the 2008 helicopter hovering reinforcement learning competition. The two approaches perform similarly (and in some cases GP performs better than the winner of the competition), even in the case where unknown wind is added to the dynamic system and control is based on structures evolved previously, that is, the evolved controllers have good generalization capability.

scholarly journals A review on carrier aircraft dispatch path planning and control on deck

2020 ◽  
Author(s):  
Xinwei WANG ◽  
Jie LIU ◽  
Xichao SU ◽  
Haijun PENG ◽  
Xudong ZHAO ◽  
...  
Keyword(s):  
Path Planning ◽  
Planning And Control ◽  
And Control

Differential-Flatness-Based Planning and Control of a Wheeled Mobile Manipulator—Theory and Experiment

2011 ◽  
Vol 16 (4) ◽  
pp. 768-773 ◽  
Author(s):  
Chin Pei Tang ◽  
Patrick T. Miller ◽  
Venkat N. Krovi ◽  
Ji-Chul Ryu ◽  
Sunil K. Agrawal
Keyword(s):  
Mobile Manipulator ◽  
Differential Flatness ◽  
Planning And Control ◽  
And Control ◽  
Theory And Experiment
Sign in / Sign up

Export Citation Format

Share Document