Jekyll2026-04-20T08:00:39+00:00https://damanikjosh.com/feed.xmlAI/Robotics Engineer at CarbonSix Robotics. Research focuses on robot navigation, multi-agent decision planning, and machine learning for robotics. Blog about autonomous systems, robotics research, and technical insights. Joshua J. Damanik2026-04-17T00:00:00+00:002026-04-17T00:00:00+00:00https://damanikjosh.com/blog/carbonsix-robotics<p>I’m excited to announce that I’m joining <a href="https://www.carbon6robotics.com/">CarbonSix Robotics</a> as an AI/Robotics Engineer!</p> <p>This marks a new chapter after my postdoctoral research at KAIST. I look forward to applying my background in autonomous navigation, multi-agent systems, and machine learning to build real-world robotics solutions at CarbonSix Robotics.</p> <p>Stay tuned for more updates on what’s ahead!</p>Joshua J. Damanik

Thrilled to start a new chapter as an AI/Robotics Engineer at CarbonSix Robotics, working on cutting-edge robotics and AI systems.

2025-08-18T00:00:00+00:002025-08-18T00:00:00+00:00https://damanikjosh.com/blog/postdoc-kaistJoshua J. Damanik

Excited to start my new role as a postdoctoral researcher at KAIST.

2025-07-11T00:00:00+00:002025-07-11T00:00:00+00:00https://damanikjosh.com/blog/talks-traceid<p><strong>Topic:</strong> Data-driven Approaches for Autonomous Robot Navigation</p> <iframe width="100%" height="405" src="https://www.youtube.com/embed/7lvIaAtt2jM?si=CfsGi4DGt6ymkFWZ" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen=""></iframe>Joshua J. Damanik

Shared insights on data-driven navigation approaches at TraceID, exploring how machine learning is transforming autonomous robot navigation systems.

2025-06-09T00:00:00+00:002025-06-09T00:00:00+00:00https://damanikjosh.com/blog/phd-defense<p><img src="/assets/images/phd-defense-1.jpg" alt="Defense photo 1" /></p> <p><img src="/assets/images/phd-defense-2.jpg" alt="Defense photo 2" /></p> <!-- Paper: [LiCS: Navigation using Learned-imitation on Cluttered Space](/publications/2024-12-16-lics) -->Joshua J. Damanik

Officially defended my PhD dissertation, completing my doctoral research on autonomous navigation systems and marking a major milestone in my academic journey.

2025-05-20T00:00:00+00:002025-05-20T00:00:00+00:00https://damanikjosh.com/blog/icra2025-lics<p><img src="/assets/images/icra2025-lics.png" alt="Presentation picture" /></p>Joshua J. Damanik

Successfully presented our LiCS navigation research at ICRA 2025, sharing our breakthrough approach to autonomous robot navigation in cluttered environments.

2025-05-19T00:00:00+00:002025-05-19T00:00:00+00:00https://damanikjosh.com/blog/icra2025-doctoral-consortium<p><img src="/assets/images/icra2025-doctoral-consortium.jpg" alt="ICRA 2025 Doctoral Consoritum poster" /></p> <h2 id="icra-2025-doctoral-consortium-experience">ICRA 2025 Doctoral Consortium Experience</h2> <p>I had the privilege of participating in the Doctoral Consortium at the IEEE International Conference on Robotics and Automation (ICRA) 2025. This competitive program brings together PhD students from around the world to present their research and receive feedback from distinguished faculty mentors.</p> <h3 id="research-presentation">Research Presentation</h3> <p>My poster focused on autonomous navigation systems in cluttered environments, highlighting:</p> <ul> <li><strong>LiCS (Learned-imitation on Cluttered Space)</strong> navigation approach</li> <li><strong>JALAN-Sim</strong> high-performance simulation environment</li> <li>Applications from <strong>BARN Challenge competitions</strong></li> <li>Future directions in <strong>sim-to-real transfer</strong></li> </ul> <h3 id="key-benefits">Key Benefits</h3> <p>The consortium provided valuable opportunities for:</p> <ul> <li>Receiving constructive feedback on doctoral research</li> <li>Networking with international PhD students and faculty</li> <li>Learning about career paths in academia and industry</li> <li>Gaining exposure to cutting-edge robotics research</li> </ul> <p>This experience has been instrumental in shaping the direction of my remaining doctoral work and future research collaborations.</p>Joshua J. Damanik

Had the opportunity to present my doctoral research at the ICRA 2025 Doctoral Consortium, sharing insights on navigation systems and learning from the robotics research community.

2024-11-01T00:00:00+00:002024-11-01T00:00:00+00:00https://damanikjosh.com/blog/f1tenth<p><img src="/assets/images/f1tenth-lics-ki.jpeg" alt="F1tenth" /></p> <p>Last week, we competed in the 3rd F1tenth Korea Championship and brought home the 7th prize! We competed against 36 teams from different universities across Asia. 🙌</p> <p>Through this challenge, we made a prototype of F1 racing car hardware 1/10 of its size, and developed agile navigation stacks using ROS 2 that can navigate in a challenging dynamics of high speed car and avoid dynamic obstacles.</p> <p>This wouldn’t have been possible without our amazing team, consisting of grad students from LiCS of AE KAIST. A big shoutout to Chala Adane, Minjo Jung, and Byeongmin Jeong! ✈️</p> <p>I’m still in the early stages of my research journey on learning-based agile robots, but I’m excited to see where this takes us. I can’t wait to take on the next challenge and continue my research in this exciting field.</p>Joshua J. Damanik

Our team brought home the 7th prize at the F1tenth Korea Championship, showcasing autonomous racing capabilities with high-speed navigation and dynamic obstacle avoidance.

2024-09-18T00:00:00+00:002024-09-18T00:00:00+00:00https://damanikjosh.com/blog/daejeon-startup<p><img src="/assets/images/daejeon-startup.jpg" alt="Daejeon Startup" /></p> <p>We participated in a startup education program supported by the <a href="https://ccei.creativekorea.or.kr/">Daejeon Center for Creative Economy and Innovation</a>. Coming up with a startup pitch idea for an autonomous bed robot, our mission was to help prevent injuries among healthcare professionals by removing one tedious task that requires two or more professionals: moving the patient’s bed.</p> <h2 id="presentation-highlights">Presentation highlights</h2> <p><img src="/assets/images/startup-bedrobot-1.jpg" alt="Robobed-1" /></p> <p><img src="/assets/images/startup-bedrobot-2.jpg" alt="Robobed-2" /></p> <h2 id="prototype-video">Prototype video</h2> <div class="text-center"> <iframe width="315" height="560" src="https://www.youtube.com/embed/MnTV5qx_yTE" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" allowfullscreen=""></iframe> </div>Joshua J. Damanik

Explore our autonomous hospital bed robot prototype designed for safe patient transportation in healthcare facilities.

2024-05-16T00:00:00+00:002024-05-16T00:00:00+00:00https://damanikjosh.com/blog/barn2024-hardware<p><img src="/assets/images/barn-challenge.png" alt="F1tenth" /></p> <h2 id="barn-challenge-2024-hardware-competition-results">BARN Challenge 2024 Hardware Competition Results</h2> <p>After securing first place in the simulation competition, our <strong>LiCS-KI</strong> team advanced to the physical finals of the BARN Challenge 2024 at ICRA in Yokohama. We’re proud to announce that we <strong>won first place</strong> in the hardware competition, successfully completing <strong>6 out of 9 trials</strong> in real-world obstacle courses.</p> <h3 id="hardware-competition-results">Hardware Competition Results</h3> <p>The physical competition involved navigating a real Clearpath Jackal robot through three different obstacle courses made of cardboard boxes. Each team had 30 minutes to complete five timed trials per course, with the top three trials counted. Success was measured by reaching the goal without any collisions.</p> <table> <thead> <tr> <th>Rangking</th> <th>Team</th> <th>Success / Total Trials</th> <th>Institution</th> </tr> </thead> <tbody> <tr> <td><strong>1</strong></td> <td><strong>LiCS-KI</strong></td> <td><strong>6/9</strong></td> <td><strong>Korea Advanced Institute of Science and Technology</strong></td> </tr> <tr> <td>2</td> <td>MLDA_EEE</td> <td>5/9 (78.8s)</td> <td>Nanyang Technological University, Singapore</td> </tr> <tr> <td>3</td> <td>AIMS</td> <td>5/9 (108.8s)</td> <td>The Hong Kong Polytechnic University</td> </tr> </tbody> </table> <p><em>Source: <a href="https://cs.gmu.edu/~xiao/Research/BARN_Challenge/BARN_Challenge24.html">BARN Challenge 2024 Official Results</a> (<a href="https://web.archive.org/web/20240703221248/https://cs.gmu.edu/~xiao/Research/BARN_Challenge/BARN_Challenge24.html">Archive</a>)</em></p> <h3 id="about-the-physical-competition">About the Physical Competition</h3> <p>The hardware competition tested the real-world capabilities of navigation systems that performed well in simulation. Key challenges included:</p> <ul> <li><strong>Sim-to-Real Gap</strong>: Dealing with real-world factors like wheel friction, motor dynamics, and sensor noise</li> <li><strong>Time Pressure</strong>: 30 minutes per obstacle course with multiple trial attempts</li> <li><strong>Physical Constraints</strong>: Navigating through tightly constrained spaces with cardboard obstacles</li> <li><strong>Onboard Computation</strong>: Limited to Intel i3 CPU with 16GB RAM (no GPU available)</li> </ul> <h3 id="our-achievement">Our Achievement</h3> <p>Winning both the simulation and hardware competitions demonstrates the robustness of our LiCS (Learned-imitation on Cluttered Space) approach. Our behavior cloning method with Transformer neural networks proved effective not only in simulation but also in real-world scenarios with all their inherent uncertainties.</p> <p>The victory showcases the practical applicability of our navigation system for real-world robotics applications, from search and rescue operations to autonomous delivery in constrained environments.</p> <h3 id="competition-format">Competition Format</h3> <ul> <li><strong>Three obstacle courses</strong> with different layouts and difficulty levels</li> <li><strong>Five timed trials</strong> per course (30 minutes total per course)</li> <li><strong>Top three trials</strong> counted for final scoring</li> <li><strong>Success criteria</strong>: Reach goal without collision</li> <li><strong>Tiebreaker</strong>: Fastest average traversal time for teams with equal success rates</li> </ul> <p>This dual victory in both simulation and hardware validates our approach’s effectiveness across the complete development pipeline from virtual testing to real-world deployment.</p>Joshua J. Damanik

Our LiCS navigation system won first place in the BARN Challenge 2024 physical finals, demonstrating superior real-world performance with 6/9 successful trials.

2024-05-08T00:00:00+00:002024-05-08T00:00:00+00:00https://damanikjosh.com/blog/barn2024-simulation<h2 id="barn-challenge-2024-simulation-results">BARN Challenge 2024 Simulation Results</h2> <p>The Benchmark Autonomous Robot Navigation (BARN) Challenge 2024 at ICRA brought together teams from around the world to test their navigation systems in highly constrained environments. Our <strong>LiCS-KI</strong> team achieved <strong>first place</strong> in the simulation competition with a score of <strong>0.4762</strong>, earning us an invitation to compete in the physical finals.</p> <h3 id="simulation-competition-results">Simulation Competition Results</h3> <p>The simulation competition evaluated navigation systems across 50 test environments using a standardized metric that considers success rate, traversal time, and environment difficulty. Here are the complete results:</p> <table> <thead> <tr> <th>Ranking</th> <th>Team</th> <th>Score</th> <th>Institution</th> </tr> </thead> <tbody> <tr> <td><strong>1</strong></td> <td><strong>LiCS-KI</strong></td> <td><strong>0.4762</strong></td> <td><strong>Korea Advanced Institute of Science and Technology</strong></td> </tr> <tr> <td>2</td> <td>AIMS</td> <td>0.4723</td> <td>The Hong Kong Polytechnic University</td> </tr> <tr> <td>3</td> <td>EIT-NUS</td> <td>0.3795</td> <td>Eastern Institute of Technology, Ningbo</td> </tr> <tr> <td>4</td> <td>MLDA_EEE</td> <td>0.2476</td> <td>Nanyang Technological University, Singapore</td> </tr> <tr> <td>5</td> <td>Default DWA^b</td> <td>0.1656</td> <td>Baseline method</td> </tr> </tbody> </table> <p>^b = baseline methods</p> <p><em>Source: <a href="https://cs.gmu.edu/~xiao/Research/BARN_Challenge/BARN_Challenge24.html">BARN Challenge 2024 Official Results</a> (<a href="https://web.archive.org/web/20240703221248/https://cs.gmu.edu/~xiao/Research/BARN_Challenge/BARN_Challenge24.html">Archive</a>)</em></p> <h3 id="about-the-competition">About the Competition</h3> <p>The BARN Challenge tests autonomous navigation systems in highly constrained environments using a standardized Clearpath Jackal robot with 2D LiDAR. Teams must navigate from start to goal as quickly as possible without collisions across 300 pre-generated environments of varying difficulty.</p>Joshua J. Damanik

Our LiCS navigation system dominated the BARN Challenge 2024 simulation competition, achieving the highest score of 0.4762 among 27 participating teams and earning an invitation to the physical finals.