Spaces:
Running
Running
Download index.html from CALM-Dataset/README: direct link, hf CLI and curl.
- Browser
- Download file 3.65 kB
-
https://huggingface.co/spaces/CALM-Dataset/README/resolve/main/index.html
- Command line
-
hf download hf://spaces/CALM-Dataset/README/index.html
-
curl -L -o index.html https://huggingface.co/spaces/CALM-Dataset/README/resolve/main/index.html
3.65 kB
| <html lang="en"> | |
| <head> | |
| <meta charset="utf-8"> | |
| <meta name="viewport" content="width=device-width, initial-scale=1"> | |
| <title>CALM</title> | |
| <style> | |
| :root{--bg:#fff;--fg:#1c2230;--mut:#5b6475;--card:#f4f6fa;--line:#dde2ec;--acc:#1f5fbf} | |
| @media (prefers-color-scheme:dark){:root{--bg:#12151c;--fg:#e8ebf2;--mut:#9aa3b5;--card:#1b2030;--line:#2b3146;--acc:#6ea3ff}} | |
| *{box-sizing:border-box} | |
| body{margin:0;background:var(--bg);color:var(--fg);font:16px/1.6 system-ui,-apple-system,"Segoe UI",sans-serif} | |
| main{max-width:820px;margin:0 auto;padding:48px 16px 64px} | |
| h1{font-size:2.4rem;margin:0;letter-spacing:.02em} | |
| .sub{color:var(--mut);margin:2px 0 6px} | |
| .tag{font-style:italic;color:var(--acc);margin:0 0 32px} | |
| p{margin:0 0 16px} | |
| ul{margin:0 0 16px;padding-left:22px} | |
| li{margin:0 0 8px} | |
| h2{font-size:1.05rem;margin:36px 0 12px;text-transform:uppercase;letter-spacing:.08em;color:var(--mut)} | |
| .grid{display:grid;grid-template-columns:repeat(auto-fit,minmax(240px,1fr));gap:12px} | |
| a.card{display:block;background:var(--card);border:1px solid var(--line);border-radius:10px;padding:14px;color:inherit;text-decoration:none} | |
| a.card:hover{border-color:var(--acc)} | |
| a.card b{color:var(--acc)} | |
| a.card small{display:block;color:var(--mut);margin-top:4px} | |
| a{color:var(--acc)} | |
| .foot{color:var(--mut);font-size:.9rem;margin-top:40px} | |
| </style> | |
| </head> | |
| <body> | |
| <main> | |
| <h1>CALM</h1> | |
| <p class="sub">Comfort-Aware Longitudinal Motion</p> | |
| <p class="tag">Slow down for the bump, not for the sake of it.</p> | |
| <p>Every driver knows the moment. A speed bump comes up, you have half a second to decide, and the car answers with a jolt that should have been a ripple. CALM is an open research project about that decision: how a car can read the road ahead and ease off by exactly as much as the bump deserves, so the people inside barely notice it.</p> | |
| <p>CALM began as a bachelor thesis at TU Berlin and has grown into an open source stack for comfort-aware speed recommendation. It contributes:</p> | |
| <ul> | |
| <li><b>An open source software stack for the slowdown-depth decision:</b> a half-car simulator with nonlinear suspension, a Gymnasium environment, an acados MPC, a PPO policy and ISO 2631-1 comfort scoring.</li> | |
| <li><b>The CALM dataset:</b> 159 real bump crossings from <a href="https://huggingface.co/CARD-Data">CARD</a> (114 Germany, 45 Italy; 105 usable), an extended real-time dataset for comfort.</li> | |
| </ul> | |
| <h2>Models and data</h2> | |
| <div class="grid"> | |
| <a class="card" href="https://huggingface.co/CALM-Dataset/CALM-PPO"><b>CALM-PPO</b><small>The trained speed recommender, with its five training runs.</small></a> | |
| <a class="card" href="https://huggingface.co/datasets/CALM-Dataset/CALM-Scenarios"><b>CALM-Scenarios</b><small>Road profiles of 159 real crossings, ready to simulate.</small></a> | |
| <a class="card" href="https://huggingface.co/datasets/CALM-Dataset/CALM-Germany"><b>CALM-Germany</b><small>114 crossings with camera, depth and sensor recordings. Access on request.</small></a> | |
| <a class="card" href="https://huggingface.co/datasets/CALM-Dataset/CALM-Italy"><b>CALM-Italy</b><small>45 crossings with camera, depth and sensor recordings. Access on request.</small></a> | |
| </div> | |
| <h2>Code</h2> | |
| <p>The simulator and the planners are on <a href="https://github.com/CALM-Dataset">GitHub</a>, together with the MATLAB ride models in <a href="https://github.com/CALM-Dataset/ride-models-matlab">ride-models-matlab</a>.</p> | |
| <p class="foot">Acknowledgements: the real-road recordings build on the <a href="https://huggingface.co/CARD-Data">CARD dataset</a> (<a href="https://arxiv.org/abs/2605.05014">Elazab et al., CVPR 2026</a>).</p> | |
| </main> | |
| </body> | |
| </html> | |