You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
342 lines
15 KiB
342 lines
15 KiB
<!DOCTYPE html>
|
|
<html lang="en">
|
|
<head>
|
|
<meta charset="UTF-8">
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
|
<title>Fox CARLA ADAS Simulation Platform</title>
|
|
<link href="https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600;700&display=swap" rel="stylesheet">
|
|
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.4.0/css/all.min.css">
|
|
<style>
|
|
:root {
|
|
--bg-page: #f1f5f9; /* Slate 100 */
|
|
--bg-slide: #ffffff;
|
|
--text-main: #0f172a; /* Slate 900 */
|
|
--text-muted: #475569; /* Slate 600 */
|
|
--accent-primary: #0284c7; /* Light Blue 600 */
|
|
--accent-soft: #e0f2fe; /* Light Blue 100 */
|
|
--border-light: #cbd5e1;
|
|
--color-success: #16a34a;
|
|
--color-warning: #eab308;
|
|
--color-danger: #ef4444;
|
|
}
|
|
|
|
* {
|
|
box-sizing: border-box;
|
|
margin: 0;
|
|
padding: 0;
|
|
}
|
|
|
|
body {
|
|
background-color: var(--bg-page);
|
|
font-family: 'Inter', sans-serif;
|
|
color: var(--text-main);
|
|
display: flex;
|
|
flex-direction: column;
|
|
align-items: center;
|
|
padding: 40px 0;
|
|
gap: 40px;
|
|
}
|
|
|
|
/* 1800x900 Rigid Container for each slide */
|
|
.slide {
|
|
width: 1800px;
|
|
height: 900px;
|
|
background-color: var(--bg-slide);
|
|
box-shadow: 0 10px 30px rgba(0, 0, 0, 0.08);
|
|
border-radius: 12px;
|
|
overflow: hidden;
|
|
position: relative;
|
|
display: flex;
|
|
flex-direction: column;
|
|
padding: 80px 100px;
|
|
border: 1px solid var(--border-light);
|
|
flex-shrink: 0;
|
|
}
|
|
|
|
/* Typography */
|
|
h1 { font-size: 72px; font-weight: 700; color: var(--text-main); line-height: 1.1; margin-bottom: 24px; letter-spacing: -1px; }
|
|
h2 { font-size: 56px; font-weight: 700; color: var(--accent-primary); margin-bottom: 20px; border-bottom: 4px solid var(--accent-soft); padding-bottom: 12px; display: inline-block; }
|
|
h3 { font-size: 32px; font-weight: 600; margin-bottom: 16px; color: var(--text-main); }
|
|
h4 { font-size: 24px; font-weight: 600; color: var(--accent-primary); margin-bottom: 10px; }
|
|
p { font-size: 26px; line-height: 1.6; color: var(--text-muted); margin-bottom: 24px; }
|
|
|
|
ul { margin-left: 32px; margin-bottom: 24px; }
|
|
li { font-size: 26px; line-height: 1.6; color: var(--text-muted); margin-bottom: 12px; }
|
|
|
|
.bold { font-weight: 600; color: var(--text-main); }
|
|
.highlight { color: var(--accent-primary); font-weight: 600; }
|
|
|
|
/* Slide specific background for Title Slide */
|
|
.slide-title {
|
|
background-image: linear-gradient(rgba(255, 255, 255, 0.85), rgba(255, 255, 255, 0.95)), url('assets/title_bg.png');
|
|
background-size: cover;
|
|
background-position: center;
|
|
justify-content: center;
|
|
align-items: center;
|
|
text-align: center;
|
|
}
|
|
|
|
.slide-title h1 {
|
|
font-size: 96px;
|
|
margin-bottom: 30px;
|
|
}
|
|
|
|
.slide-title p {
|
|
font-size: 36px;
|
|
max-width: 1200px;
|
|
margin: 0 auto;
|
|
}
|
|
|
|
.company-logo {
|
|
position: absolute;
|
|
top: 60px;
|
|
left: 80px;
|
|
font-size: 48px;
|
|
font-weight: 700;
|
|
color: var(--accent-primary);
|
|
}
|
|
|
|
/* Layouts */
|
|
.body-grid-2 {
|
|
display: grid;
|
|
grid-template-columns: 1fr 1fr;
|
|
gap: 60px;
|
|
flex-grow: 1;
|
|
margin-top: 20px;
|
|
}
|
|
|
|
.body-grid-3 {
|
|
display: grid;
|
|
grid-template-columns: 1fr 1fr 1fr;
|
|
gap: 40px;
|
|
flex-grow: 1;
|
|
margin-top: 20px;
|
|
}
|
|
|
|
/* Custom UI Components */
|
|
.card {
|
|
background: #f8fafc;
|
|
border: 2px solid var(--border-light);
|
|
border-radius: 12px;
|
|
padding: 30px;
|
|
display: flex;
|
|
flex-direction: column;
|
|
}
|
|
|
|
.card-icon {
|
|
font-size: 40px;
|
|
color: var(--accent-primary);
|
|
margin-bottom: 20px;
|
|
}
|
|
|
|
.alert-box {
|
|
background-color: var(--accent-soft);
|
|
border-left: 6px solid var(--accent-primary);
|
|
padding: 24px;
|
|
border-radius: 0 8px 8px 0;
|
|
margin: 20px 0;
|
|
}
|
|
|
|
.alert-box.danger {
|
|
background-color: #fef2f2;
|
|
border-left-color: var(--color-danger);
|
|
}
|
|
|
|
.alert-box.success {
|
|
background-color: #f0fdf4;
|
|
border-left-color: var(--color-success);
|
|
}
|
|
|
|
/* Empty Image Placeholders */
|
|
.image-placeholder {
|
|
width: 100%;
|
|
height: 100%;
|
|
background-color: #f8fafc;
|
|
border: 4px dashed var(--accent-primary);
|
|
border-radius: 16px;
|
|
display: flex;
|
|
flex-direction: column;
|
|
align-items: center;
|
|
justify-content: center;
|
|
text-align: center;
|
|
padding: 40px;
|
|
color: var(--accent-primary);
|
|
}
|
|
|
|
.image-placeholder.horizontal {
|
|
min-height: 400px;
|
|
}
|
|
|
|
.image-placeholder i {
|
|
font-size: 64px;
|
|
margin-bottom: 24px;
|
|
}
|
|
|
|
.image-placeholder .title {
|
|
font-size: 28px;
|
|
font-weight: 700;
|
|
margin-bottom: 12px;
|
|
}
|
|
|
|
.image-placeholder .instructions {
|
|
font-size: 20px;
|
|
color: var(--text-muted);
|
|
max-width: 80%;
|
|
}
|
|
|
|
.tag {
|
|
display: inline-block;
|
|
background-color: var(--accent-soft);
|
|
color: var(--accent-primary);
|
|
padding: 6px 16px;
|
|
border-radius: 20px;
|
|
font-size: 18px;
|
|
font-weight: 600;
|
|
margin-right: 10px;
|
|
margin-bottom: 10px;
|
|
}
|
|
|
|
</style>
|
|
</head>
|
|
<body>
|
|
|
|
<!-- Slide 1: Title -->
|
|
<div class="slide slide-title">
|
|
<div class="company-logo">FOX <span style="color:var(--text-main);">ADAS</span></div>
|
|
<div style="background: rgba(255,255,255,0.7); padding: 60px; border-radius: 24px; backdrop-filter: blur(10px); border: 2px solid white; box-shadow: 0 10px 40px rgba(0,0,0,0.05);">
|
|
<h1>High-Fidelity Deterministic<br><span class="highlight">Radar Simulation</span></h1>
|
|
<p>Moving from bounding-box emulation to mathematically pure, hardware-configurable physics validating the Shenron Pipeline.</p>
|
|
</div>
|
|
</div>
|
|
|
|
<!-- Slide 2: The Vision & Physical Approach -->
|
|
<div class="slide">
|
|
<h2>The Physical Foundation: 1/R⁴ Physics</h2>
|
|
<div class="body-grid-2">
|
|
<div>
|
|
<p>Standard simulator bounding-boxes bypass the complex realities of electromagnetic propagation. The Shenron engine enforces strict free-space physics for absolute accuracy.</p>
|
|
|
|
<div class="card" style="margin-bottom: 30px;">
|
|
<h3><i class="card-icon fa-solid fa-bolt"></i> Milestone R4: Pure Physics</h3>
|
|
<p>We abandoned artificial density and distance normalizations. All generated scatterers now strictly follow the <span class="bold highlight">Radar Range Equation (1/R⁴)</span>. A building at distance naturally drops in power compared to a vehicle up close.</p>
|
|
</div>
|
|
|
|
<div class="card">
|
|
<h3><i class="card-icon fa-solid fa-car-burst"></i> Deterministic Coordinate Control</h3>
|
|
<p>Standard Traffic Manager leads to high variance. Using a <span class="bold">Spawn-and-Move</span> logic with enforced Velocity overrides guarantees complex scenarios (like left-turn cut-ins) occur at the exact same millisecond every run.</p>
|
|
</div>
|
|
</div>
|
|
<div>
|
|
<div class="image-placeholder">
|
|
<i class="fa-solid fa-atom"></i>
|
|
<div class="title">Insert Screenshot: 1/R⁴ Contrast</div>
|
|
<div class="instructions">Provide a side-by-side or CFAR output showing how distant heavy clutter is naturally attenuated while the closer vehicle is correctly highlighted due to the inverse square law path loss.</div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
|
|
<!-- Slide 3: Unprecedented Configurability -->
|
|
<div class="slide">
|
|
<h2>Unprecedented Configurability: "Knobs & Dials"</h2>
|
|
<div class="body-grid-2">
|
|
<div>
|
|
<p>The Shenron architecture eliminates hardcoded physical scalars. Instead, it exposes a "Control Panel" mimicking real hardware tuning. <span class="bold">If we do it on the test track, we can do it in the simulation.</span></p>
|
|
|
|
<h3>Supported Hardware Profiles</h3>
|
|
<div style="margin-bottom: 20px;">
|
|
<span class="tag">TI AWRL1432 (ADAS)</span>
|
|
<span class="tag">Radarbook (Research)</span>
|
|
<span class="tag">TI Cascade (MIMO)</span>
|
|
</div>
|
|
|
|
<ul style="margin-top: 30px;">
|
|
<li><span class="highlight">Bandwidth (B) & Chirps:</span> Accurately adjust range and doppler resolution directly reflecting radar specifications.</li>
|
|
<li><span class="highlight">System Gain Calibration (110dB):</span> Modify the global signal chain gain ($P_t G_t G_r$) without touching the core physics engine.</li>
|
|
<li><span class="highlight">Antenna Arrays (nRx/nTx):</span> Instantly swap between 6 virtual receivers (1432) or 8 virtual receivers (Radarbook) to measure DSP beamforming limits.</li>
|
|
<li><span class="highlight">Noise Amplitude:</span> Dynamically inject AWGN thermal noise to test CFAR floor robustness.</li>
|
|
</ul>
|
|
</div>
|
|
<div>
|
|
<div class="image-placeholder">
|
|
<i class="fa-solid fa-sliders"></i>
|
|
<div class="title">Insert Code/UI Screenshot: Customizing Radar</div>
|
|
<div class="instructions">Please insert a screenshot showing `ConfigureRadar.py` or the specific JSON payload being passed via the dashboard to demonstrate how easily we swap between a 1432 profile and a Radarbook profile.</div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
|
|
<!-- Slide 4: Deep Observability & Metrology -->
|
|
<div class="slide">
|
|
<h2>Deep Observability: The Metrology Suite</h2>
|
|
<div class="body-grid-2">
|
|
<div>
|
|
<p>Instead of treating synthetic radar output as a "black box," our new pipeline visualizes the entire signal chain. This allows engineers to cross-validate ADC output against physical ground truth.</p>
|
|
|
|
<div class="alert-box success">
|
|
<h4>The "Radar Blue" Standard</h4>
|
|
<p>We instituted phase-preserving <span class="bold">Doppler-Slice Synthesis</span> to replace artifact-heavy coherent integration, resulting in pristine, sharp heatmaps.</p>
|
|
</div>
|
|
|
|
<ul>
|
|
<li><span class="bold">Range-Doppler (RD):</span> Extracts target separation and velocity, preventing velocity zeroing.</li>
|
|
<li><span class="bold">Range-Azimuth (RA):</span> Confirms azimuthal accuracy utilizing Zero-Tilt Symmetry (120° FOV perfectly aligned to boresight).</li>
|
|
<li><span class="bold">CFAR Gate:</span> Visualizes adaptive thresholds distinguishing targets from the synthesized noise floor.</li>
|
|
</ul>
|
|
</div>
|
|
<div>
|
|
<div class="image-placeholder">
|
|
<i class="fa-solid fa-layer-group"></i>
|
|
<div class="title">Insert Screenshot: 3-Plot Metrology Suite</div>
|
|
<div class="instructions">Insert a screenshot of the Foxglove layout showing the 3 core metrology graphs (RD, RA, and CFAR) running alongside the 3D Pointcloud view to illustrate deep observability.</div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
|
|
<!-- Slide 5: Major Breakthroughs & Bug Squashing Engine -->
|
|
<div class="slide">
|
|
<h2>Major Breakthroughs & Bug Squashing Engine</h2>
|
|
<p>Achieving this level of physical simulation required identifying and tearing down several legacy miscalculations that corrupted early models.</p>
|
|
|
|
<div class="body-grid-2">
|
|
<div class="card">
|
|
<h3><i class="fa-solid fa-satellite-dish"></i> The Isotropic Illumination Fix</h3>
|
|
<p>The deepest physics problem resolved. Early simulation allowed side-targets at 80° to return 100% power, masking forward vehicles. <br><br>We implemented <span class="highlight">Horizontal (Azimuth) & Vertical (Elevation) Directional Gain Patterns</span>. Clutter at wide angles is now correctly attenuated by ~15-20 dB, letting the true target dominate.</p>
|
|
</div>
|
|
<div class="card" style="display: flex; gap: 20px; flex-direction: column;">
|
|
<div>
|
|
<h4><i class="fa-solid fa-bug" style="color:var(--color-danger); margin-right:8px;"></i> The Cos(Cos) Reflection Error</h4>
|
|
<p style="font-size:22px; margin-bottom:0;">Recovered 46% of lost signal energy by tracking down a double-cosine application in the Open3D coordinate translation pipeline.</p>
|
|
</div>
|
|
<div style="height:1px; background:var(--border-light); width:100%;"></div>
|
|
<div>
|
|
<h4><i class="fa-solid fa-bug" style="color:var(--color-danger); margin-right:8px;"></i> Floating Point Data Packing</h4>
|
|
<p style="font-size:22px; margin-bottom:0;">Resolved the infamous "0.0 velocity" bug by utilizing `np.view(np.uint32)` to correctly deserialize perfectly packed 32-bit semantic tags.</p>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
|
|
<!-- Slide 6: The Full Automation Pipeline -->
|
|
<div class="slide">
|
|
<h2>The Full Automation Pipeline</h2>
|
|
<p>A completely automated workflow enabling one-click testbenches, fully orchestrated via a web dashboard.</p>
|
|
|
|
<div class="image-placeholder horizontal" style="background-image: linear-gradient(rgba(248, 250, 252, 0.9), rgba(248, 250, 252, 0.9)), url('assets/pipeline_bg.png'); background-size: cover; background-position: center;">
|
|
<i class="fa-solid fa-network-wired" style="color: var(--accent-primary);"></i>
|
|
<div class="title">Insert Graphic/Screenshot: Pipeline & Dashboard</div>
|
|
<div class="instructions" style="color:var(--text-main);">
|
|
Place a diagram or screenshot here showing the flow:<br><br>
|
|
<b>1. GUI Dashboard (with Hardware GPU Idle Mode)</b> → <b>2. CARLA Simulator</b> → <b>3. Shenron Physics</b> → <b>4. MCAP Serializer</b> → <b>5. Foxglove Studio</b>
|
|
</div>
|
|
</div>
|
|
|
|
<div style="margin-top: 40px; text-align: center;">
|
|
<p>From deterministic scenario configuration to a 3D Foxglove validation pointcloud — without manual intervention.</p>
|
|
</div>
|
|
</div>
|
|
|
|
</body>
|
|
</html>
|