Sponsored By
May 2, 2024
Thursday
Over his 25-plus-year career, Kumar has successfully scaled businesses at major multinationals including General Motors, General Electric, and Honeywell. In this keynote, he will share some lessons he has learned and how they can be applied to accelerate the transformation of industry with robotics.
Join us for an interactive exploration into Disney’s innovative use of robotics. Disney researchers Mortiz Baecher, Morgan Pope, and Tony Dohi will demonstrate Disney’s latest robots and explain how imagination and engineering are bringing some of Disney’s beloved characters to life.
Recreating intelligence in machines has been one of computer science’s grand challenges since Alan Turing. He proposed imitating the human mind and envisioned a symbolic approach. Today, AI has followed a different path, relying on vast datasets and compute in an attempt to brute-force cognition. This approach is based on a loose understanding of the brain, but does it represent the end point for machine thought or a stop on the journey?
In this talk, Prof. James Marshall will propose that the structural limitations of deep learning and technologies such as SLAM (simultaneous localization and mapping) prevent them from robustly solving the problem of “thinking” in a way that would satisfy Turing. Far from being “all about scale,” standard approaches are already presenting diminishing returns, he said. Marshall will present an alternative approach, based on understanding whole-brain function, not of humans to begin with, but simple organisms such as insects. He will explore how solving the problem of ‘solving’ thinking most likely has its roots in solving the problem of moving autonomously in the world.
In addition, Marshall will tie theory with practice by showing the short-term payoff of this approach: substantially more efficient and robust autonomy for robots in the real world.
Generative AI is revolutionizing the software industry, but how can this breakthrough be applied to robotics? This panel will discuss the applications of large language models (LLMs) and text generation applications to robotics. It will also explore fundamental ways generative AI can be applied to robotics design, model training, simulation, control, human-machine interaction and more.
The Robot Operating System (ROS) is gaining popularity in the robotics industry because it is an open-source platform that solves a common problem: trajectory calculation for complex, multi-axis machines. However, users are faced with the issue of sending the trajectory information in a reliable, deterministic way. Software libraries that handle the low-level EtherCAT and CANopen communications can bridge the gap between the controller and the drive, simplifying the overall development of complex motion control applications.
If the method of trajectory transmission is unreliable, undesired behavior may occur, such as choppy motion, damaged payloads, and error conditions. The DS402 Protocol for Motion Control has defined Interpolated Position Mode as a means of standardizing the control of multiple coordinated axes through the transmission of synchronization (SYNC) pulses and process data objects (PDO’s).
High-resolution trajectories result in high data rates that must be handled by both the controller and drive. Some controllers use real-time operating systems to deal with the high data rates. Another approach utilizes data buffers in the firmware of both the controller and drive to provide forgiveness for controller latency. In either case, engineers designing robotic systems will find that low-level software to process the data is necessary to achieve reliable, high performance motion control. Processing libraries such as the Copley Motion Library (CML) provide easy implementation that integrates seamlessly with the MoveIt2 API and utilizes the DS402 Protocol to deliver smooth, synchronous motion over the CANopen or EtherCAT networks.
The need for increased productivity and lower cost are driving the growth of
robotics in various industries. In the past the push for robotic automation was
mostly constrained to industries with well-defined challenges in controlled
environments such as manufacturing industry and automated logistics. The nature
of the applications allows for straightforward, top-down optimization of the
robotic application and its subsystems. Although being complex in nature, the
resulting requirements for drive systems are often defined as part of a portfolio.
The customer selects the appropriate drive solution in terms of cost, efficiency,
power, precision, etc.
Today, robotics is entering new markets with weakly defined problem sets and a
broad spectrum of possible environment conditions. Examples of this trend are
mobile robots in inspection and agriculture, collaborative robots and medical
robots for assisted living and rehabilitation. Developing solutions for these
applications leads to multi-objective optimization problems with higher complexity
compared to classical applications. Top-down optimization approaches are
rendered obsolete because of increasingly important two-way interactions across
system layers. Robotic system developers and drive system suppliers benefit from
close cooperation to achieve the holistic optimization of the application including
its drive system.
This contribution outlines the challenges of novel robotic applications and shows
how drive systems as a sub-system are impacted. Our approach of integrating
component and robotic application models into a single, holistic drive system
optimization methodology is shown in detail. A focus is put on how the
cooperation of system integrator and sub-system supplier is changing with our
approach. Lastly, we provide insight into how the development of classical
applications also benefits from the holistic optimization methodology.
Page 1 of 3
Resources
Subscribe to The Robot Report
Advertise with us
For registration or logistic questions, contact events@wtwhmedia.com
Advertise with us
For registration or logistic questions, contact events@wtwhmedia.com
Sponsorship Opportunities
Colleen Sepich
Events Sales Director
csepich@wtwhmedia.com
857-260-1360
Heather Herbert
Event Sales Manager
hherbert@wtwhmedia.com
512-760-0570
Events Sales Director
csepich@wtwhmedia.com
857-260-1360
Heather Herbert
Event Sales Manager
hherbert@wtwhmedia.com
512-760-0570
Copyright © 2024 WTWH Media, LLC. All Rights Reserved.