The field of robotics has been rapidly developing in recent years, and the work related to training robotic agents with reinforcement learning has been a major focus of research. This survey reviews the application of reinforcement learning for pick-and-place operations, a task that a logistics robot can be trained to complete without support from a robotics engineer. To introduce this topic, we first review the fundamentals of reinforcement learning and various methods of policy optimization, such as value iteration and policy search. Next, factors which have an impact on the pick-and-place task, such as reward shaping, imitation learning, pose estimation, and simulation environment are examined. Following the review of the fundamentals and key factors for reinforcement learning, we present an extensive review of all methods implemented by researchers in the field to date. The strengths and weaknesses of each method from literature are discussed, and details about the contribution of each manuscript to the field are reviewed. The concluding critical discussion of the available literature, and the summary of open problems indicates that experiment validation, model generalization, and grasp pose selection are topics that require additional research.
With recent impressive clinical results of targeted alpha therapy using 225Ac, significant effort has been directed towards providing a reliable and sufficient supply of 225Ac to enable widespread using of 225Ac-radiopharmaceuticals. TRIUMF has begun production of 225Ac via spallation of thorium metal with 480 MeV protons. As part of this program, a new 225Ac-production target system capable of withstanding the power deposited by the proton beam was designed and its performance simulated over a range of potential operating parameters. Special attention was given to heat transfer and stresses within the target components. The target was successfully tested in two irradiations with a 72–73 µA proton beam for a duration of 36.5 h. The decay corrected activity at end of irradiation (average ± standard deviation) was (524 ± 21) MBq (14.2 mCi) and (86 ± 13) MBq (2.3 mCi) for 225Ac and 225Ra, respectively. These correspond to saturation yields of 72.5 MBq/µA for 225Ac and 17.6 MBq/µA for 225Ra. Longer irradiations and production scale-up are planned in the future.
The majority of robots in factories today are operated with conventional control strategies that require individual programming on a task-by-task basis, with no margin for error. As an alternative to the rudimentary operation planning and task-programming techniques, machine learning has shown significant promise for higher-level task planning, with the development of reinforcement learning (RL)-based control strategies. This paper reviews the implementation of combined traditional and RL control for simulated and real environments to validate the RL approach for standard industrial tasks such as reach, grasp, and pick-and-place. The goal of this research is to bring intelligence to robotic control so that robotic operations can be completed without precisely defining the environment, constraints, and the action plan. The results from this approach provide optimistic preliminary data on the application of RL to real-world robotics.
1 March 2019 in Journal of Medical Imaging and Radiation Sciences