Chris Heckman /cs/ en Robots can save us if they can see us: Heckman receives CAREER award /cs/2024/10/15/robots-can-save-us-if-they-can-see-us-heckman-receives-career-award <span>Robots can save us if they can see us: Heckman receives CAREER award</span> <span><span>Emily Adams</span></span> <span><time datetime="2024-10-15T14:07:19-06:00" title="Tuesday, October 15, 2024 - 14:07">Tue, 10/15/2024 - 14:07</time> </span> <div> <div class="imageMediaStyle focal_image_wide"> <img loading="lazy" src="/cs/sites/default/files/styles/focal_image_wide/public/2024-10/MARBLE%20robot%20edgar%20mine.JPG?h=95f4d75d&amp;itok=s5T8XTud" width="1200" height="800" alt="A SPOT robot with a light enters a dark mine tunnel"> </div> </div> <div role="contentinfo" class="container ucb-article-categories" itemprop="about"> <span class="visually-hidden">Categories:</span> <div class="ucb-article-category-icon" aria-hidden="true"> <i class="fa-solid fa-folder-open"></i> </div> <a href="/cs/taxonomy/term/457"> Research </a> </div> <div role="contentinfo" class="container ucb-article-tags" itemprop="keywords"> <span class="visually-hidden">Tags:</span> <div class="ucb-article-tag-icon" aria-hidden="true"> <i class="fa-solid fa-tags"></i> </div> <a href="/cs/taxonomy/term/478" hreflang="en">Chris Heckman</a> </div> <a href="/cs/node/421">Grace Wilson</a> <div class="ucb-article-content ucb-striped-content"> <div class="container"> <div class="paragraph paragraph--type--article-content paragraph--view-mode--default 3"> <div class="ucb-article-row-subrow row"> <div class="ucb-article-text col-lg d-flex align-items-center" itemprop="articleBody"> <div><p dir="ltr"><span>Autonomous robots could save human lives more easily if they could “see” and react better in adverse environmental conditions. By pursuing the possibilities of using millimeter wave radar for robotic perception,&nbsp;</span><a href="/cs/christoffer-heckman" rel="nofollow"><span>Christoffer Heckman</span></a><span> is making this fundamental shift possible.</span></p><p dir="ltr"><span>An associate professor of computer science at ϳԹ, Heckman will receive $600,000 over the next five years through the National Science Foundation's CAREER award for this research.</span></p><p dir="ltr"><span>Currently, most robots use sensors based on the visible spectrum of light, like cameras or lasers. In environments with smoke, fog or dust, however, visible light bounces off these particles.</span></p><p dir="ltr"><span>Robots, like humans, can't plan their movements accurately if they don't know where they are or what is around them.</span></p><p dir="ltr"><span>"Humans operating in a visually degraded environment are in trouble. We cannot solve that problem, but incorporating millimeter wave radar could enable our robots to do things that even humans can't do,"&nbsp; Heckman said.</span></p><p dir="ltr"><span>This is because millimeter waves pass through smoke, fog and dust.&nbsp;</span></p><p class="lead"><span>A new path</span></p><p dir="ltr"><span>Traditionally, Heckman explained, radar has been viewed with skepticism for these kinds of tasks. The sensors have been too large and energy-intensive for agile robots. The long wavelength of radar creates complex, confused signals.</span></p><p dir="ltr"><span>With the advent of new, smaller system-on-a-chip radar sensors, the traditional energy and size limitations have been removed. This leaves the complexity of radar waveform signals.</span></p><p dir="ltr"><span>"This is a fascinating problem," Heckman explained. "People really understand how radar works, down to equations that have existed for almost a century, but radar can be difficult to precisely interpret in cluttered environments. It bounces around within an enclosed area, and can pass right through small objects."</span></p><p dir="ltr"><span>Heckman's solution is to fuse the knowledge we have about electromagnetic waves with supervised machine learning.</span></p><p dir="ltr"><span>Datasets from high-fidelity optical sensors are paired with low-fidelity radar signals of the same scene. Machine learning then cleans the radar signal to match the high-fidelity scene. This training then can be used to build clear radar reconstructions of environments where optical sensors are obscured.</span></p><p dir="ltr"><span>This powerful synthesis of physics and computer science stands to dramatically improve the capability of radar as a perception sensor.</span></p><p class="lead"><span>Beyond sensing</span></p><p dir="ltr"><span>Heckman has further plans as well. He wants to use this advance to support quick and accurate actions and replanning for autonomous systems.</span></p><p dir="ltr"><span>Robotic thinking has traditionally followed the saying "sense, plan, act." A robot understands a scene, plans its route according to its inputs, and acts on that plan. Segmenting these activities, however, can lead to slow movement and inability to react to changes.</span></p><p dir="ltr"><span>Heckman seeks to use radar in conjunction with optical and lidar sensors to improve navigation strategies as a robot is navigating a space, allowing it to respond more quickly to changes.</span></p><p dir="ltr"><span>Robots that can plan for themselves better and can see into obscured spaces have a valuable role in search-and-rescue, firefighting and space missions.</span></p><p dir="ltr"><span>Heckman's MARBLE team has&nbsp;</span><a href="/engineering/2023/11/17/building-next-generation-autonomous-robots-serve-humanity" rel="nofollow"><span>used robots to explore dark caves</span></a><span> through the DARPA Subterranean Challenge and as a firefighting assistant finding active embers. As the research advances made possible by this CAREER Award take shape, where will robots be able to see next?&nbsp;</span></p></div> </div> <div class="ucb-article-content-media ucb-article-content-media-right col-lg"> <div> <blockquote class="ucb-article-blockquote"> <div class="ucb-article-blockquote-icon font-gold"> <i class="fa-solid fa-quote-left"></i> </div> <div class="ucb-article-blockquote-text"> <div>Humans operating in a visually degraded environment are in trouble. We cannot solve that problem, but incorporating millimeter wave radar could enable our robots to do things that even humans can't do." - Chris Heckman</div> </div></blockquote> </div> </div> </div> </div> </div> </div> <div>Radar breakthrough in robotic sensing to help systems see and act in smoke, darkness recognized by $600,000 National Science Foundation award.</div> <h2> <div class="paragraph paragraph--type--ucb-related-articles-block paragraph--view-mode--default"> <div>Off</div> </div> </h2> <div>Traditional</div> <div>0</div> <div> <div class="imageMediaStyle large_image_style"> <img loading="lazy" src="/cs/sites/default/files/styles/large_image_style/public/2024-10/MARBLE%20robot%20edgar%20mine.JPG?itok=sYDLZxSI" width="1500" height="1000" alt="A SPOT robot with a light enters a dark mine tunnel"> </div> <span class="media-image-caption"> <p>A SPOT robot with a light enters a dark mine tunnel.</p> </span> </div> <div>On</div> <div>White</div> Tue, 15 Oct 2024 20:07:19 +0000 Emily Adams 2507 at /cs Is the World Ready for Self-Driving Cars? /cs/2023/11/27/world-ready-self-driving-cars <span>Is the World Ready for Self-Driving Cars?</span> <span><span>Anonymous (not verified)</span></span> <span><time datetime="2023-11-27T10:29:39-07:00" title="Monday, November 27, 2023 - 10:29">Mon, 11/27/2023 - 10:29</time> </span> <div> <div class="imageMediaStyle focal_image_wide"> <img loading="lazy" src="/cs/sites/default/files/styles/focal_image_wide/public/article-thumbnail/screenshot_2023-11-27_at_10.23.31_am.png?h=195f6103&amp;itok=PqD5Qhi-" width="1200" height="800" alt="An illustration of two people talking in an futuristic autonomous vehicle "> </div> </div> <div role="contentinfo" class="container ucb-article-tags" itemprop="keywords"> <span class="visually-hidden">Tags:</span> <div class="ucb-article-tag-icon" aria-hidden="true"> <i class="fa-solid fa-tags"></i> </div> <a href="/cs/taxonomy/term/478" hreflang="en">Chris Heckman</a> <a href="/cs/taxonomy/term/559" hreflang="en">Leanne Hirschfield</a> <a href="/cs/taxonomy/term/485" hreflang="en">Majid Zamani</a> <a href="/cs/taxonomy/term/549" hreflang="en">Sidney D'mello</a> </div> <span>Daniel Oberhaus</span> <div class="ucb-article-content ucb-striped-content"> <div class="container"> <div class="paragraph paragraph--type--article-content paragraph--view-mode--default"> <div class="ucb-article-content-media ucb-article-content-media-above"> <div> <div class="paragraph paragraph--type--media paragraph--view-mode--default"> </div> </div> </div> <div class="ucb-article-text d-flex align-items-center" itemprop="articleBody"> </div> </div> </div> </div> <div>Autonomous vehicles are hitting the road in cities across the U.S. Can they be trusted? Researchers from the Department of Computer Science weigh in. External link to the Coloradan Alumni Magazine. </div> <script> window.location.href = `/coloradan/2023/11/06/world-ready-self-driving-cars`; </script> <h2> <div class="paragraph paragraph--type--ucb-related-articles-block paragraph--view-mode--default"> <div>Off</div> </div> </h2> <div>Traditional</div> <div>0</div> <div>On</div> <div>White</div> Mon, 27 Nov 2023 17:29:39 +0000 Anonymous 2399 at /cs Building next generation autonomous robots to serve humanity /cs/2023/11/17/building-next-generation-autonomous-robots-serve-humanity <span>Building next generation autonomous robots to serve humanity</span> <span><span>Anonymous (not verified)</span></span> <span><time datetime="2023-11-17T16:16:23-07:00" title="Friday, November 17, 2023 - 16:16">Fri, 11/17/2023 - 16:16</time> </span> <div> <div class="imageMediaStyle focal_image_wide"> <img loading="lazy" src="/cs/sites/default/files/styles/focal_image_wide/public/article-thumbnail/edgar_mines_lab_2023_090.png?h=29bc86dc&amp;itok=Q-3FvZI4" width="1200" height="800" alt="Edgar Mine robot"> </div> </div> <div role="contentinfo" class="container ucb-article-tags" itemprop="keywords"> <span class="visually-hidden">Tags:</span> <div class="ucb-article-tag-icon" aria-hidden="true"> <i class="fa-solid fa-tags"></i> </div> <a href="/cs/taxonomy/term/478" hreflang="en">Chris Heckman</a> </div> <span>Jeff Zehnder</span> <div class="ucb-article-content ucb-striped-content"> <div class="container"> <div class="paragraph paragraph--type--article-content paragraph--view-mode--default"> <div class="ucb-article-content-media ucb-article-content-media-above"> <div> <div class="paragraph paragraph--type--media paragraph--view-mode--default"> </div> </div> </div> <div class="ucb-article-text d-flex align-items-center" itemprop="articleBody"> </div> </div> </div> </div> <div>One thousand feet underground, a four-legged creature scavenges through tunnels in pitch darkness. The sound of its movements echo eerily off the walls, but it is not to be feared – this is no wild animal; it is an autonomous rescue robot.</div> <script> window.location.href = `/engineering/2023/11/17/building-next-generation-autonomous-robots-serve-humanity`; </script> <h2> <div class="paragraph paragraph--type--ucb-related-articles-block paragraph--view-mode--default"> <div>Off</div> </div> </h2> <div>Traditional</div> <div>0</div> <div>On</div> <div>White</div> Fri, 17 Nov 2023 23:16:23 +0000 Anonymous 2397 at /cs Keeping water on the radar: Machine learning to aid in essential water cycle measurement /cs/2022/05/20/keeping-water-radar-machine-learning-aid-essential-water-cycle-measurement <span>Keeping water on the radar: Machine learning to aid in essential water cycle measurement</span> <span><span>Anonymous (not verified)</span></span> <span><time datetime="2022-05-20T11:45:44-06:00" title="Friday, May 20, 2022 - 11:45">Fri, 05/20/2022 - 11:45</time> </span> <div> <div class="imageMediaStyle focal_image_wide"> <img loading="lazy" src="/cs/sites/default/files/styles/focal_image_wide/public/article-thumbnail/untitled_1920_x_200_px.png?h=6c045699&amp;itok=BXvwOnw-" width="1200" height="800" alt="Water and radar abstract image"> </div> </div> <div role="contentinfo" class="container ucb-article-categories" itemprop="about"> <span class="visually-hidden">Categories:</span> <div c