Designfax weekly eMagazine

Subscribe Today!

Archives

View Archives

Partners

Manufacturing Center
Product Spotlight

Modern Applications News
Metalworking Ideas For
Today's Job Shops

Tooling and Production
Strategies for large
metalworking plants

Overhung load adaptors provide load support and contamination protection

Overhung load adaptors (OHLA) provide both overhung radial and axial load support to protect electrified mobile equipment motors from heavy application loads, extending the lifetime of the motor and alleviating the cost of downtime both from maintenance costs and loss of production. They seal out dirt, grime, and other contaminants too. Zero-Max OHLAs are available in an extensive offering of standard models (including Extra-Duty options) for typical applications or customized designs.
Learn more.

Why choose electric for linear actuators?

Tolomatic has been delivering a new type of linear motion technology that is giving hydraulics a run for its money. Learn the benefits of electric linear motion systems, the iceberg principle showing total cost of ownership, critical parameters of sizing, and conversion tips.
Get this informative e-book. (No registration required)

New AC hypoid inverter-duty gearmotors

Bodine Electric Company introduces 12 new AC inverter-duty hypoid hollow shaft gearmotors. These type 42R-25H2 and 42R-30H3 drives combine an all-new AC inverter-duty, 230/460-VAC motor with two hypoid gearheads. When used with an AC inverter (VFD) control, these units deliver maintenance-free and reliable high-torque output. They are ideal for conveyors, gates, packaging, and other industrial automation equipment that demands both high torque and low power consumption from the driving gearmotor.
Learn more.

Next-gen warehouse automation: Siemens, Universal Robots, and Zivid partner up

Universal Robots, Siemens, and Zivid have created a new solution combining UR's cobot arms with Siemens' SIMATIC Robot Pick AI software and Zivid's 3D sensors to create a deep-learning picking solution for warehouse automation and intra-logistics fulfillment. It works regardless of object shape, size, opacity, or transparency and is a significant leap in solving the complex challenges faced by the logistics and e-commerce sectors.
Read the full article.

Innovative DuoDrive gear and motor unit is UL/CSA certified

The DuoDrive integrated gear unit and motor from NORD DRIVE-SYSTEMS is a compact, high-efficiency solution engineered for users in the fields of intralogistics, pharmaceutical, and the food and beverage industries. This drive combines a IE5+ synchronous motor and single-stage helical gear unit into one compact housing with a smooth, easy-to-clean surface. It has a system efficiency up to 92% and is available in two case sizes with a power range of 0.5 to 4.0 hp.
Learn more.

BLDC flat motor with high output torque and speed reduction

Portescap's 60ECF brushless DC slotted flat motor is the newest frame size to join its flat motor portfolio. This 60-mm BLDC motor features a 38.2-mm body length and an outer-rotor slotted configuration with an open-body design, allowing it to deliver improved heat management in a compact package. Combined with Portescap gearheads, it delivers extremely high output torque and speed reduction. Available in both sensored and sensorless options. A great choice for applications such as electric grippers and exoskeletons, eVTOLs, and surgical robots.
Learn more and view all the specs.

Application story: Complete gearbox and coupling assembly for actuator system

Learn how GAM engineers not only sized and selected the appropriate gear reducers and couplings required to drive two ball screws in unison using a single motor, but how they also designed the mounting adapters necessary to complete the system. One-stop shopping eliminated unnecessary components and resulted in a 15% reduction in system cost.
Read this informative GAM blog.

Next-gen motor for pump and fan applications

The next evolution of the award-winning Aircore EC motor from Infinitum is a high-efficiency system designed to power commercial and industrial applications such as HVAC fans, pumps, and data centers with less energy consumption, reduced emissions, and reduced waste. It features an integrated variable frequency drive and delivers upward of 93% system efficiency, as well as class-leading power and torque density in a low-footprint package that is 20% lighter than the previous version. Four sizes available.
Learn more.

Telescoping linear actuators for space-constrained applications

Rollon's new TLS telescoping linear actuators enable long stroke lengths with minimal closed lengths, which is especially good for applications with minimal vertical clearance. These actuators integrate seamlessly into multi-axis systems and are available in two- or three-stage versions. Equipped with a built-in automated lubrication system, the TLS Series features a synchronized drive system, requiring only a single motor to achieve motion. Four sizes (100, 230, 280, and 360) with up to 3,000-mm stroke length.
Learn more.

Competitively priced long-stroke parallel gripper

The DHPL from Festo is a new generation of pneumatic long-stroke grippers that offers a host of advantages for high-load and high-torque applications. It is interchangeable with competitive long-stroke grippers and provides the added benefits of lighter weight, higher precision, and no maintenance. It is ideal for gripping larger items, including stacking boxes, gripping shaped parts, and keeping bags open. It has high repetition accuracy due to three rugged guide rods and a rack-and-pinion design.
Learn more.

Extend your range of motion: Controllers for mini motors

FAULHABER has added another extremely compact Motion Controller without housing to its product range. The new MC3603 controller is ideal for integration in equipment manufacturing and medical tech applications. With 36 V and 3 A (peak current 9 A), it covers the power range up to 100 W and is suitable for DC motors with encoder, brushless drives, or linear motors.
Learn more.

When is a frameless brushless DC motor the right choice?

Frameless BLDC motors fit easily into small, compact machines that require high precision, high torque, and high efficiency, such as robotic applications where a mix of low weight and inertia is critical. Learn from the experts at SDP/SI how these motors can replace heavier, less efficient hydraulic components by decreasing operating and maintenance costs. These motors are also more environmentally friendly than others.
View the video.

Tiny and smart: Step motor with closed-loop control

Nanotec's new PD1-C step motor features an integrated controller and absolute encoder with closed-loop control. With a flange size of merely 28 mm (NEMA 11), this compact motor reaches a max holding torque of 18 Ncm and a peak current of 3 A. Three motor versions are available: IP20 protection, IP65 protection, and a motor with open housing that can be modified with custom connectors. Ideal for applications with space constraints, effectively reducing both wiring complexity and installation costs.
Learn more.

Closed loop steppers drive new motion control applications

According to the motion experts at Performance Motion Devices, when it comes to step motors, the drive technique called closed loop stepper is making everything old new again and driving a burst of interest in the use of two-phase step motors. It's "winning back machine designers who may have relegated step motors to the category of low cost but low performance."
Read this informative Performance Motion Devices article.

Intelligent compact drives with extended fieldbus options

The intelligent PD6 compact drives from Nanotec are now available with Profinet and EtherNet/IP. They combine motor, controller, and encoder in a space-saving package. With its 80-mm flange and a rated power of 942 W, the PD6-EB is the most powerful brushless DC motor of this product family. The stepper motor version has an 86-mm flange (NEMA 34) and a holding torque up to 10 Nm. Features include acceleration feed forward and jerk-limited ramps. Reduced installation time and wiring make the PD6 series a highly profitable choice for machine tools, packaging machines, or conveyor belts.
Learn more.

Such a good little droid -- U.S. Army researchers develop new tools to train robots

By Joyce M. Conant, ARL

Researchers at the U.S. Army Research Laboratory in Maryland and The University of Texas at Austin have developed new techniques for robots or computer programs to learn how to perform tasks by interacting with a human instructor. The findings of the study were presented and published Feb. 5 at the Thirty-Second Association for the Advancement of Artificial Intelligence Conference in New Orleans, LA.

The purpose of the AAAI conference is to promote research in artificial intelligence and scientific exchange among AI researchers, practitioners, scientists, and engineers in affiliated disciplines.

"AAAI is one of the premiere conferences in artificial intelligence," said Dr. Garrett Warnell, ARL researcher. "We are excited to be able to present some of our recent work in this area and to solicit valuable feedback from the research community."

ARL and UT researchers considered a specific case where a human provides real-time feedback in the form of critique. First introduced as TAMER, or Training an Agent Manually via Evaluative Reinforcement, a new algorithm called "Deep TAMER" has been introduced. It is an extension of TAMER that uses deep learning -- a class of machine learning algorithms that are loosely inspired by the brain -- to provide a robot the ability to learn how to perform tasks by viewing video streams in a short amount of time with a human trainer.

The "Deep TAMER" is an extension of TAMER that uses deep learning -- a class of machine learning algorithms that are loosely inspired by the brain -- to provide a robot the ability to learn how to perform tasks by viewing video streams in a short amount of time with a human trainer. [U.S. Army graphic]

 

 

 

 

Researchers considered situations where a human teaches an agent how to behave by observing it and providing critique, i.e., "good job" or "bad job" -- similar to the way a person might train a dog to do a trick. ARL and UT Austin jointly extended earlier work in this field to enable this type of training for robots or computer programs that currently see the world through images, which is an important first step in designing learning agents that can operate in the real world.

"This research advance has been made possible in large part by our unique collaboration arrangement in which Dr. Warnell, an ARL employee, has been embedded in my lab at UT Austin," said Dr. Peter Stone. "This arrangement has allowed for a much more rapid and deeper exchange of ideas than is typically possible with remote research collaborations."

Many current techniques in artificial intelligence require robots to interact with their environment for extended periods of time to learn how to optimally perform a task. During this process, the agent might perform actions that may not only be wrong (a robot running into a wall), but catastrophic (a robot running off the side of a cliff). Researchers believe help from humans will speed things up for the agents, and help them avoid potential pitfalls.

As a first step, the researchers demonstrated Deep TAMER's success by using it with 15 minutes of human-provided feedback to train an agent to perform better than humans on the Atari game of bowling -- a task that has proven difficult for even state-of-the-art methods in artificial intelligence. Deep-TAMER-trained agents exhibited superhuman performance, besting both their amateur trainers and, on average, an expert human Atari player.

ARL researchers believe the Army of the future will consist of Soldiers and autonomous teammates working side-by-side. While both humans and autonomous agents can be trained in advance, the team will inevitably be asked to perform tasks (for example, search-and-rescue or surveillance) in new environments they have not seen before. In these situations, humans are remarkably good at generalizing their training, but current artificially intelligent agents are not.

"If we want these teams to be successful, we need new ways for humans to be able to quickly teach their autonomous teammates how to behave in new environments," Warnell said. "We want this instruction to be as easy and natural as possible. Deep TAMER, which requires only critique feedback from the human, shows that this type of real-time instruction can be successful in certain, more-realistic scenarios."

Dr. Garrett Warnell, researcher at ARL, presents new machine learning algorithms developed to train robots at the Thirty-Second Association for the Advancement of Artificial Intelligence Conference. [U.S. Army photo]

 

 

Over the years, several artificial intelligence researchers have considered a number of ways to use humans to quickly teach an autonomous agent to perform a task. One very popular method is called learning from demonstration, where the agent watches a human perform the task and then tries to imitate the human. But what if there isn't someone who can demonstrate the task? Any basketball fan can tell you that you don't have to know how to shoot a three-pointer in order to be able to tell if someone else is good or bad at it. Allowing autonomous agents to leverage this type of knowledge via critical feedback from a human was the focus of TAMER, developed by collaborator Dr. Peter Stone, a professor at The University of Texas at Austin, along with his former Ph.D. student, Brad Knox.

"TAMER is excellent work, but it implicitly requires an expert programmer to provide the agent with a special kind of advanced knowledge," Warnell explained. "With Deep TAMER, we no longer need the expert programmer."

Additionally, using Deep TAMER the researchers found the autonomous agents were able to achieve super-human performance. "They learned so well that they were quickly able to perform better than their human instructors," added ARL researcher Dr. Nicholas Waytowich. "This is an exciting prospect as it breaks the notion that a student is only as good as the teacher."

In the near term, researchers are interested in exploring the applicability of their newest technique in a wider variety of environments: for example, video games other than Atari Bowling and additional simulation environments to better represent the types of agents and environments found when fielding robots in the real world.

"This effort, supported by a Directors Strategic Initiative award, represents our initial steps in understanding the role of humans in human-AI interaction, in particular understanding how humans can train AI agents to perform tasks," said Dr. Vernon Lawhern, ARL researcher. "In addition, it is also important to try and minimize the amount of human interaction required, as having a human constantly teach AI is infeasible in most situations. Therefore, understanding not only what to convey to an AI agent, but how to convey it, and how to best use that information, will be important to developing flexible human-AI teams of the future."

Ultimately, the researchers want autonomous agents that can quickly and safely learn from their human teammates in a wide variety of styles such as demonstration, natural language instruction, and critique.

Published March 2018

Rate this article