update some dates

Author: Haoru Xue

comments/feed/index.xml

@@ -11,7 +11,7 @@
 	<atom:link href="https://drive-lab-cmu.github.io/comments/feed/" rel="self" type="application/rss+xml" />
 	<link>https://drive-lab-cmu.github.io/</link>
 	<description>Driverless Intelligent Vehicle Lab - Carnegie Mellon University</description>
-	<lastBuildDate>Thu, 04 Jul 2024 00:26:29 +0000</lastBuildDate>
+	<lastBuildDate>Sat, 06 Jul 2024 20:05:34 +0000</lastBuildDate>
 	<sy:updatePeriod>
 	hourly	</sy:updatePeriod>
 	<sy:updateFrequency>

feed/index.xml

@@ -12,7 +12,7 @@
 	<atom:link href="https://drive-lab-cmu.github.io/feed/" rel="self" type="application/rss+xml" />
 	<link>https://drive-lab-cmu.github.io/</link>
 	<description>Driverless Intelligent Vehicle Lab - Carnegie Mellon University</description>
-	<lastBuildDate>Thu, 04 Jul 2024 00:26:29 +0000</lastBuildDate>
+	<lastBuildDate>Sat, 06 Jul 2024 20:05:34 +0000</lastBuildDate>
 	<language>en-US</language>
 	<sy:updatePeriod>
 	hourly	</sy:updatePeriod>

index.html

@@ -247,7 +247,7 @@ <h2 class="wp-block-heading">Latest</h2>
 
 
 
-<li>1/31/2024: Three papers accepted to ICRA 2024.</li>
+<li>1/31/2024: Five papers accepted to ICRA 2024.</li>
 </ul>
 </div></main>
 

people/index.html

@@ -240,7 +240,7 @@ <h1 class="wp-block-heading">Publications</h1>
 
 <div class="wp-block-media-text is-stacked-on-mobile" style="grid-template-columns:33% auto">
 <figure class="wp-block-media-text__media"><img loading="lazy" decoding="async" width="640" height="360" src="https://drive-lab-cmu.github.io/wp-content/uploads/2024/06/SafeDPA.gif" alt="" class="wp-image-521 size-full"></figure><div class="wp-block-media-text__content">
-<p><strong>Safe Deep Policy Adaptation</strong><br><em>Wenli Xiao*, Tairan He*, John Dolan, Guanya Shi</em><br>ICRA 2024 | <a href="https://arxiv.org/abs/2310.08602" data-type="link" data-id="https://arxiv.org/abs/2310.08602">arxiv</a> | <a href="https://sites.google.com/view/safe-deep-policy-adaptation" data-type="link" data-id="https://sites.google.com/view/safe-deep-policy-adaptation">website</a> | <a href="https://github.com/LeCAR-Lab/SafeDPA" data-type="link" data-id="https://github.com/LeCAR-Lab/SafeDPA">code</a> | <a href="https://x.com/_wenlixiao/status/1790909857496961300" data-type="link" data-id="https://x.com/_wenlixiao/status/1790909857496961300">social media</a> | <a href="https://www.youtube.com/watch?v=PkyRzlRQVbE" data-type="link" data-id="https://www.youtube.com/watch?v=PkyRzlRQVbE">talk</a><br><br>This paper jointly tackles policy adaptation and safe reinforcement learning with safety guarantees. Comprehensive experiments on (1) classic control problems (Inverted Pendulum), (2) simulation benchmarks (Safety Gym), and (3) a real-world agile robotics platform (RC Car) demonstrate great superiority of SafeDPA in both safety and task performance, over state-of-the-art baselines.</p>
+<p><strong>Safe Deep Policy Adaptation</strong><br><em>Wenli Xiao*, Tairan He*, John M. Dolan, Guanya Shi</em><br>ICRA 2024 | <a href="https://arxiv.org/abs/2310.08602" data-type="link" data-id="https://arxiv.org/abs/2310.08602">arxiv</a> | <a href="https://sites.google.com/view/safe-deep-policy-adaptation" data-type="link" data-id="https://sites.google.com/view/safe-deep-policy-adaptation">website</a> | <a href="https://github.com/LeCAR-Lab/SafeDPA" data-type="link" data-id="https://github.com/LeCAR-Lab/SafeDPA">code</a> | <a href="https://x.com/_wenlixiao/status/1790909857496961300" data-type="link" data-id="https://x.com/_wenlixiao/status/1790909857496961300">social media</a> | <a href="https://www.youtube.com/watch?v=PkyRzlRQVbE" data-type="link" data-id="https://www.youtube.com/watch?v=PkyRzlRQVbE">talk</a><br><br>This paper jointly tackles policy adaptation and safe reinforcement learning with safety guarantees. Comprehensive experiments on (1) classic control problems (Inverted Pendulum), (2) simulation benchmarks (Safety Gym), and (3) a real-world agile robotics platform (RC Car) demonstrate great superiority of SafeDPA in both safety and task performance, over state-of-the-art baselines.</p>
 </div>
 </div>
 
@@ -256,7 +256,15 @@ <h1 class="wp-block-heading">Publications</h1>
 
 <div class="wp-block-media-text is-stacked-on-mobile" style="grid-template-columns:33% auto">
 <figure class="wp-block-media-text__media"><img loading="lazy" decoding="async" width="300" height="169" src="https://drive-lab-cmu.github.io/wp-content/uploads/2024/04/gail.gif" alt="" class="wp-image-63 size-full"></figure><div class="wp-block-media-text__content">
-<p><strong>WROOM: An Autonomous Driving Approach for Off-Road Navigation</strong><br><em>Dvij Kalaria, Shreya Sharma, Sarthak Bhagat, Haoru Xue, John M. Dolan</em><br>ICRA 2024 Workshop | <a href="https://arxiv.org/abs/2404.08855">arxiv</a> | <a href="https://sites.google.com/view/wroom-utd/home">website</a> | <a href="https://github.com/dvij542/OffTerSim">code</a><br><br>WROOM brings a gym environment for training off-road driving RL policy. We use PPO + CBF to train an end-to-end agent to safely navigate in the real world.</p>
+<p><strong>WROOM: An Autonomous Driving Approach for Off-Road Navigation</strong><br><em>Dvij Kalaria,&nbsp;Shreya Sharma,&nbsp;Sarthak Bhagat,&nbsp;Haoru Xue,&nbsp;John M. Dolan</em><br>ICRA 2024 Workshop |&nbsp;<a href="https://arxiv.org/abs/2404.08855">arxiv</a>&nbsp;|&nbsp;<a href="https://sites.google.com/view/wroom-utd/home">website</a>&nbsp;|&nbsp;<a href="https://github.com/dvij542/OffTerSim">code</a><br><br>WROOM brings a gym environment for training off-road driving RL policy. We use PPO + CBF to train an end-to-end agent to safely navigate in the real world.</p>
+</div>
+</div>
+
+
+
+<div class="wp-block-media-text is-stacked-on-mobile has-base-2-background-color has-background" style="grid-template-columns:33% auto">
+<figure class="wp-block-media-text__media"><img loading="lazy" decoding="async" width="365" height="259" src="https://drive-lab-cmu.github.io/wp-content/uploads/2024/07/ncbf_flying_inv_pend.png" alt="" class="wp-image-594 size-full" srcset="https://drive-lab-cmu.github.io/wp-content/uploads/2024/07/ncbf_flying_inv_pend.png 365w, https://drive-lab-cmu.github.io/wp-content/uploads/2024/07/ncbf_flying_inv_pend-300x213.png 300w" sizes="(max-width: 365px) 100vw, 365px"></figure><div class="wp-block-media-text__content">
+<p><strong><strong>Safe Control Under Input Limits with Neural Control Barrier Functions</strong></strong><br><em>Simin Liu, Changliu Liu, John M. Dolan</em><br>CoRL 2023 | <a href="https://arxiv.org/abs/2211.11056" data-type="link" data-id="https://arxiv.org/abs/2211.11056">arxiv</a> | <a href="https://github.com/sliu2019/input_limit_cbf" data-type="link" data-id="https://github.com/sliu2019/input_limit_cbf">code</a> | <a href="https://www.siminl.com/pdfs/neural_cbf_slides.pdf" data-type="link" data-id="https://www.siminl.com/pdfs/neural_cbf_slides.pdf">slides</a><br><br>We created a scalable dynamics adaptation technique using adversarial training of neural CBFs. Essentially, our method trades the theoretical guarantees of safety for scalability and strong empirical guarantees (>99% safe). Currently, this class of methods has been shown to scale to >20D. This includes complex systems, like balancing quadrotors and many-linked manipulators.</p>
 </div>
 </div>
 

publications/index.html

@@ -203,7 +203,7 @@ <h1 class="wp-block-heading">Research Areas</h1>
 
 
 
-<h2 class="wp-block-heading">Adverserial Multi-Agent Systems</h2>
+<h2 class="wp-block-heading">Adversarial Multi-Agent Systems</h2>