diff --git a/scripts/analyse-collaborative-complex.ipynb b/scripts/analyse-collaborative-complex.ipynb
new file mode 100644
index 0000000..660670b
--- /dev/null
+++ b/scripts/analyse-collaborative-complex.ipynb
@@ -0,0 +1,446 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 65,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import sys\n",
+    "import os\n",
+    "\n",
+    "import re\n",
+    "import json\n",
+    "import statistics\n",
+    "import argparse\n",
+    "import itertools\n",
+    "from pathlib import Path\n",
+    "from dataclasses import dataclass\n",
+    "\n",
+    "# print(f\"{os.getcwd()=}\")\n",
+    "\n",
+    "from ldj import ldj\n",
+    "from utils import *\n",
+    "\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "# from matplotlib.font_manager import FontProperties\n",
+    "import matplotlib.font_manager as fm\n",
+    "from matplotlib.patches import FancyBboxPatch\n",
+    "from matplotlib.patches import PathPatch\n",
+    "from matplotlib.path import get_path_collection_extents\n",
+    "import seaborn as sns\n",
+    "\n",
+    "from rich import print, pretty\n",
+    "from tabulate import tabulate\n",
+    "from typing import  Iterable\n",
+    "import pretty_errors\n",
+    "from catppuccin import PALETTE\n",
+    "from IPython.display import display, HTML\n",
+    "\n",
+    "pretty.install()\n",
+    "\n",
+    "EXPERIMENT_DIR = Path(\"../experiments/collaborative-complex\")\n",
+    "assert EXPERIMENT_DIR.is_dir() and EXPERIMENT_DIR.exists()\n",
+    "\n",
+    "flavor = PALETTE.latte.colors\n",
+    "\n",
+    "data = dict()\n",
+    "\n",
+    "@dataclass\n",
+    "class Results:\n",
+    "    with_tracking: dict\n",
+    "    without_tracking: dict\n",
+    "\n",
+    "results = Results(dict(), dict())\n",
+    "\n",
+    "with open(EXPERIMENT_DIR / \"tracking-true.json\") as f:\n",
+    "    results.with_tracking = json.load(f)\n",
+    "\n",
+    "with open(EXPERIMENT_DIR / \"tracking-false.json\") as f:\n",
+    "    results.without_tracking = json.load(f)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 55,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "@dataclass(frozen=True)\n",
+    "class Statistics:\n",
+    "    mean: float\n",
+    "    median: float\n",
+    "    stdev: float\n",
+    "    min: float\n",
+    "    max: float\n",
+    "\n",
+    "\n",
+    "    def display(self) -> None:\n",
+    "        data = [\n",
+    "            [\"Mean\", self.mean],\n",
+    "            [\"Median\", self.median],\n",
+    "            [\"Standard Deviation\", self.stdev],\n",
+    "            [\"Min\", self.min],\n",
+    "            [\"Max\", self.max]\n",
+    "        ]\n",
+    "        html_table = tabulate(data, headers=[\"Statistic\", \"Value\"], tablefmt=\"html\")\n",
+    "        centered_html_table = f\"\"\"\n",
+    "        <div style=\"display: flex; justify-content: center;\">\n",
+    "            {html_table}\n",
+    "        </div>\n",
+    "        \"\"\"\n",
+    "        # display(HTML(html_table))\n",
+    "        display(HTML(centered_html_table))\n",
+    "        # print(tabulate(data, headers=[\"Statistic\", \"Value\"], tablefmt=\"html\"))\n",
+    "\n",
+    "\n",
+    "def compute_stats(data: list[float]) -> Statistics:\n",
+    "    return Statistics(\n",
+    "        mean=np.mean(data),\n",
+    "        median=np.median(data),\n",
+    "        stdev=np.std(data),\n",
+    "        min=np.min(data),\n",
+    "        max=np.max(data),\n",
+    "    )\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "@dataclass(frozen=True)\n",
+    "class PerpendicularPositionErrorResult:\n",
+    "    errors: list[float]\n",
+    "    rmses: list[float]\n",
+    "\n",
+    "\n",
+    "def perpendicular_position_error(exported_data: dict) -> PerpendicularPositionErrorResult:\n",
+    "    errors: list[float] = []\n",
+    "    rmses: list[float] = []\n",
+    "\n",
+    "    for robot_id, robot_data in exported_data['robots'].items():\n",
+    "        color: str = robot_data['color']\n",
+    "        positions = np.array([p for p in robot_data['positions']])\n",
+    "        mission = robot_data['mission']\n",
+    "        waypoints = []\n",
+    "        for route in mission['routes']:\n",
+    "            waypoints.append(route['waypoints'][0])\n",
+    "            for wp in route['waypoints'][1:]:\n",
+    "                waypoints.append(wp)\n",
+    "\n",
+    "        waypoints = np.array(waypoints)\n",
+    "        waypoints = np.squeeze(waypoints)\n",
+    "\n",
+    "        lines: list[LinePoints] = [LinePoints(start=start, end=end) for start, end in sliding_window(waypoints, 2)]\n",
+    "        closest_projections = [closest_projection_onto_line_segments(p, lines) for p in positions]\n",
+    "\n",
+    "        error: float = np.sum(np.linalg.norm(positions - closest_projections, axis=1))\n",
+    "        rmse: float = np.sqrt(error / len(positions))\n",
+    "\n",
+    "        errors.append(error)\n",
+    "        rmses.append(rmse)\n",
+    "\n",
+    "    return PerpendicularPositionErrorResult(errors=errors, rmses=rmses)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 59,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "@dataclass(frozen=True)\n",
+    "class CollisionsResult:\n",
+    "    interrobot: int\n",
+    "    environment: int\n",
+    "\n",
+    "def collisions(exported_data: dict) -> CollisionsResult:\n",
+    "    interrobot: int = len(exported_data['collisions']['robots'])\n",
+    "    environment: int = len(exported_data['collisions']['environment'])\n",
+    "    return CollisionsResult(interrobot=interrobot, environment=environment)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# With Tracking"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Makespan"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 66,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">makespan = <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">159.92</span> seconds\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "makespan = \u001b[1;36m159.92\u001b[0m seconds\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "print(f\"makespan = {results.with_tracking['makespan']:.2f} seconds\")\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Perpendicular Position Error"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 70,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"></pre>\n"
+      ],
+      "text/plain": []
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "        <div style=\"display: flex; justify-content: center;\">\n",
+       "            <table>\n",
+       "<thead>\n",
+       "<tr><th>Statistic         </th><th style=\"text-align: right;\">       Value</th></tr>\n",
+       "</thead>\n",
+       "<tbody>\n",
+       "<tr><td>Mean              </td><td style=\"text-align: right;\">113.23      </td></tr>\n",
+       "<tr><td>Median            </td><td style=\"text-align: right;\">107.61      </td></tr>\n",
+       "<tr><td>Standard Deviation</td><td style=\"text-align: right;\"> 47.0414    </td></tr>\n",
+       "<tr><td>Min               </td><td style=\"text-align: right;\">  9.9365e-13</td></tr>\n",
+       "<tr><td>Max               </td><td style=\"text-align: right;\">316.921     </td></tr>\n",
+       "</tbody>\n",
+       "</table>\n",
+       "        </div>\n",
+       "        "
+      ],
+      "text/plain": [
+       "\u001b[1m<\u001b[0m\u001b[1;95mIPython.core.display.HTML\u001b[0m\u001b[39m object\u001b[0m\u001b[1m>\u001b[0m"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "pperror = perpendicular_position_error(results.with_tracking)\n",
+    "compute_stats(pperror.errors).display()\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Collisions"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 60,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"></pre>\n"
+      ],
+      "text/plain": []
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": [
+       "\u001b[1;35mCollisionsResult\u001b[0m\u001b[1m(\u001b[0m\u001b[33minterrobot\u001b[0m=\u001b[1;36m0\u001b[0m, \u001b[33menvironment\u001b[0m=\u001b[1;36m90\u001b[0m\u001b[1m)\u001b[0m"
+      ]
+     },
+     "execution_count": 60,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "collisions(results.with_tracking)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Without Tracking"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">makespan = <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">160.34</span> seconds\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "makespan = \u001b[1;36m160.34\u001b[0m seconds\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "print(f\"makespan = {results.without_tracking['makespan']:.2f} seconds\")\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Perpendicular Position Error"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 71,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"></pre>\n"
+      ],
+      "text/plain": []
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "        <div style=\"display: flex; justify-content: center;\">\n",
+       "            <table>\n",
+       "<thead>\n",
+       "<tr><th>Statistic         </th><th style=\"text-align: right;\">       Value</th></tr>\n",
+       "</thead>\n",
+       "<tbody>\n",
+       "<tr><td>Mean              </td><td style=\"text-align: right;\">113.23      </td></tr>\n",
+       "<tr><td>Median            </td><td style=\"text-align: right;\">107.61      </td></tr>\n",
+       "<tr><td>Standard Deviation</td><td style=\"text-align: right;\"> 47.0414    </td></tr>\n",
+       "<tr><td>Min               </td><td style=\"text-align: right;\">  9.9365e-13</td></tr>\n",
+       "<tr><td>Max               </td><td style=\"text-align: right;\">316.921     </td></tr>\n",
+       "</tbody>\n",
+       "</table>\n",
+       "        </div>\n",
+       "        "
+      ],
+      "text/plain": [
+       "\u001b[1m<\u001b[0m\u001b[1;95mIPython.core.display.HTML\u001b[0m\u001b[39m object\u001b[0m\u001b[1m>\u001b[0m"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "pperror = perpendicular_position_error(results.without_tracking)\n",
+    "compute_stats(pperror.errors).display()\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Collisions"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 63,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"></pre>\n"
+      ],
+      "text/plain": []
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": [
+       "\u001b[1;35mCollisionsResult\u001b[0m\u001b[1m(\u001b[0m\u001b[33minterrobot\u001b[0m=\u001b[1;36m0\u001b[0m, \u001b[33menvironment\u001b[0m=\u001b[1;36m90\u001b[0m\u001b[1m)\u001b[0m"
+      ]
+     },
+     "execution_count": 63,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "collisions(results.without_tracking)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}