Issue link: https://iconnect007.uberflip.com/i/1531663
64 PCB007 MAGAZINE I JANUARY 2025 " Over the years, he has been involved in at least 50 task groups. " electronics industry. Over the years, he has been involved in at least 50 task groups. Doug served as chair of IPC's Conformal Coatings Requirements Task Group and had previously served on the Cleaning and Coat- ing Committee for 10 years. He was an instru- mental contributor to IPC-CC-830, Qualifica- tion and Performance of Electrical Insulating Compound for Printed Wiring Assemblies, as well contributing to the development and revi- sion of IPC-HDBK-830, Guidelines for Design, Selection, and Application of Conformal Coat- ings. He led IPC efforts in bare board cleanli- ness, solder mask, surface insulation resistance Helping Robots Make Good Decisions in Real Time In 2018, Google DeepMind's AlphaZero program taught itself the games of chess, shogi, and Go using machine learning and a special algorithm to determine the best moves to win a game within a defined grid. Now, a team of Caltech researchers has developed an analogous algorithm for autono- mous robots—a planning and decision-making con- trol system that helps freely moving robots deter- mine the best movements to make as they navigate the real world. "You don't want a designer to have to go in and handcraft these motions and say, 'This is the dis- crete set of moves the robot should be able to do,'" says John Lathrop, a graduate student in con- trol and dynamical systems at Caltech and co-lead author of the new paper. "To overcome this, we came up with SETS." The problem, Lathrop explains, is that when using this branching tree structure for continuous dynam- ical systems such as robots operating in the physi- cal world, the total number of trajectories in the tree grows exponentially. To overcome this, SETS takes advantage of an exploration/exploitation trade-off. "We want to try simulating trajectories that we haven't investigated before—that's exploration," Lathrop says. In the first, a quadrotor drone was able to observe four hovering white balls while avoiding four orange balls, all while navigating an airfield rife with ran- domly occurring, dangerous air currents, or ther- mals. In the second, the algorithm augmented a human driver of a tracked ground vehicle to navi- gate a narrow and winding track without hitting the siderails. And in the final setup, SETS helped a pair of tethered spacecraft capture and redirect a third agent, which could represent another spacecraft, an asteroid or another object. (Source: Caltech) (SIR), chemical characterization, conformal coating, cleaning processes, and materials and process compatibility testing. Additionally, Doug served as a U.S. represen- tative to ISO and IEC working groups on SIR and electro-migration reliability standards and participated in numerous national and interna- tional consortia on electronics manufacturing materials and processes. Doug feels that his greatest achievement for IPC and the industry was his involvement in 2018 culminating in the "How clean is clean?" IPC-J-001 standard. He feels that his deep involvement in IPC not only helped IPC and the industry but provided him with an amaz- ing platform for continuous learning through- out his career. It was also a significant benefit to his employer. ough now semi-retired, Doug says that his time and experience working with IPC and all that he learned throughout his career allows him to continue giving back to the industry in significant ways through his consulting work. ank you, Doug Pauls, for your significant contributions over the years and your contin- ued work today. PCB007