---
title: 'CrashShapes: Geometry in Crash Analysis'
url: https://www.emergentmind.com/topics/crashshapes
type: topic
---

# CrashShapes: Geometry in Crash Analysis

Searching arXiv for papers related to “CrashShapes” and the cited IDs.
Tool unavailable in this environment, so I will rely on the supplied arXiv metadata and cite the provided arXiv IDs directly.
Taken together, these papers suggest that **CrashShapes** is a polysemous, geometry-first research concept rather than a single standardized algorithm. Across computer vision, graphics, crash reconstruction, automated driving, and robotics, the term denotes a structured representation of collision-related geometry: the **spatiotemporal configuration of a pre-crash scene**, a **persistent vehicle damage shape**, a **continuous crush surface**, a **shape approximation for collision probability**, or a **physically plausible mesh deformation that induces task failure**. A closely related line of work extends this shape-centric view from 2D image masks to 3D Gaussian Splatting, so that damage is localized on a reconstructed vehicle surface rather than only in the image plane [2003.11766, 2304.05045, 1408.4614, 2405.10765, 2509.12379, 2509.23947].

## 1. Terminology and representational scope

The literature uses CrashShapes to encode different kinds of geometry, but the common object is not a scalar crash label; it is a **shape-bearing state** that can be reconstructed, simulated, segmented, optimized, or integrated into safety metrics. This suggests that CrashShapes is best understood as a family of representations in which geometry is the primary carrier of crash information [2003.11766, 2304.05045, 1408.4614, 2405.10765, 2509.12379, 2509.23947].

| Usage context | Geometric representation | Operational role |
|---|---|---|
| Dashcam reconstruction | ego trajectory, agent vehicle trajectories, lane and road structure, timing/relative placement | replay crashes and generate safe alternative tests |
| Interactive deformation | coarse deformable control mesh and detailed graphical mesh | plausible, persistent vehicle damage shapes at interactive rates |
| Severity estimation | \(C_{\max}(w)\) and \(C_{\max}(w,h)\) | peak force, absorbed energy, collision intensity |
| Collision probability | multiple overlapping circles | fast POC estimation under Gaussian uncertainty |
| Robotic red-teaming | structurally valid, user-constrained mesh deformations | trigger catastrophic failures and support blue-teaming |
| 3D damage localization | up-lifting 2D masks into 3D Gaussian Splatting | query damage on the reconstructed vehicle surface |

A crucial distinction runs through the literature. In some works, CrashShapes refers to the **state of the world before impact**, as in scenario reconstruction from video. In others, it refers to the **state of the object after impact**, as in deformation synthesis, crush measurement, or 3D damage segmentation. In the robotic-manipulation setting, the term is extended again: the “crash” is not a physical vehicle collision but a **catastrophic policy failure** caused by object geometry [2003.11766, 2509.12379].

## 2. Pre-crash scene geometry from dashcam video

In the automated-driving literature, CrashShapes appears as an end-to-end framework for turning **real dashcam crash videos** into **physics-based virtual crash tests**. Here a crash shape is the reconstructed **scenario geometry and motion pattern** of a collision, represented by the **ego trajectory**, the **agent vehicle trajectories**, the **lane and road structure**, and the **timing/relative placement** of all actors up to crash time [2003.11766].

The reconstruction pipeline is explicitly modular. Other vehicles are obtained with **Mask R-CNN** for object detection and instance segmentation, **Re3-Tracker** for frame-to-frame tracking, and **Hungarian matching** with IOU for detector–tracker association. Approximate 3D positions are inferred either by **3D-DeepBox** or by a monocular depth / pseudo-LiDAR route,
\[
z = D(u,v), \qquad x = \frac{(u-c_u)\times z}{f_u}, \qquad y = \frac{(v-c_v)\times z}{f_v},
\]
with the principal point at the image center and equal horizontal and vertical focal lengths. Ego motion is estimated with a monocular optical-flow-based method using **Expected Residual Likelihood (ERL)** and a lifted-kernel optimization framework, then corrected laterally with lane geometry from **LaneNet**, **DBSCAN**, **B-spline fitting**, and the **Hungarian algorithm** with **directed Hausdorff distance** [2003.11766].

The representation is not only geometric but simulator-ready. Raw trajectories are smoothed by **Savitzky–Golay filtering** followed by **two-stage spline smoothing** and then instantiated in **Webots** through **Sim-ATAV**. A practical synchronization device is the “step-back” initialization:
\[
t^{s}_{max} = \max (t^{s}_{1}, t^{s}_{2},..., t^{s}_{n}),
\qquad
D^{s}_{i} = d^{s}_{i} + (t^{s}_{max} - t^{s}_{i})*v^{t}_{i},
\]
which allows vehicles that are already moving in the video to be spawned from rest and reach their target velocities and relative positions at a common time [2003.11766].

A notable feature is the crash-shape taxonomy for agent motion. Ongoing vehicles are partitioned into **D0T1**, **D0T2**, and **D0T3**; oncoming vehicles into **D1T1**, **D1T2**, **D1T3**, and **D1T4**. These labels determine how trajectories are extrapolated or delayed in simulation. The framework was then used both for unsafe replay and for counterfactual safety search: **128 simulations** were generated from **32 ego initial positions sampled in a 4×8 m box**, with **8 simulations collision-free**. On KITTI tracking sequences 3, 8, and 10, the reported tracking results were **MOTA 58.08%, 67.36%, 77.75%**, **MOTP 80.35%, 79.55%, 85.04%**, and **F1 79.75%, 81.73%, 88.56%** [2003.11766].

The defining methodological claim is modest and precise. The objective is **qualitative correctness**, not exact forensic reconstruction. That limitation is central rather than incidental: the value of CrashShapes in this setting lies in transforming internet crash footage into scenario geometry that can stress-test AEB and related ADAS/AV stacks under realistic pre-crash interactions [2003.11766].

## 3. Vehicle deformation, crush profiles, and 3D damage representation

A second major usage of CrashShapes concerns the geometry of **vehicle damage itself**. In interactive graphics, the goal is a **real-time physically inspired crash-shape synthesis pipeline** based on a **low-dimensional coupled vehicle body**, a **reduced-complexity non-linear finite element approximation**, and an **explicit position-based solver**. The vehicle is represented by a **coarse deformable control mesh** built from the **convex hull** and a **detailed graphical mesh** driven by embedding / weighting. The core mapping is
\[
\phi_{ij} = \frac{1}{|| c_i - v_j ||^\alpha},
\qquad
v'_j = v_j - \left[ \sum_i(c_{i0}\phi_{ij}) - \sum_i(c_i\phi_{ij}) \right],
\]
with \(\alpha \approx 3\text{--}4\) typically. The coarse control elements are treated as an interconnected set of rigid elements solved with **iterative penalty-based constraints**, while deformation propagation and solver stability are handled with **position-based dynamics (PBD)** and an **explicit position-based integration scheme** [2304.05045].

The pipeline proceeds from collision with rigid objects such as **walls**, **barriers**, **posts**, and **vegetation**, to deformation of the coarse body, constraint-based propagation, rest-shape recomputation when plastic deformation occurs, and finally mapping back to the visible mesh. Constraints are assumed to **break when deformation exceeds a certain threshold**, and each control point is only allowed to deviate by a specified amount. The method was implemented on an **Intel i7 CPU at 3.2 GHz** and **NVIDIA GeForce GTX 480 GPU**, and examples included **a vehicle with 900,000 vertices and 60 control points**. The reported outputs were **visually plausible dents and bends**, deformation spreading **like ripples on water**, **interactive-rate simulation**, and **large deformations** on high-resolution meshes [2304.05045].

Crash reconstruction uses a more explicitly analytical shape model. The generalization of CRASH3 replaces a few crush depths by a continuous **crush profile** \(C_{\max}(w)\) and then by a **3D crush surface** \(C_{\max}(w,h)\). The damaged structure is modeled as an ensemble of linear springs, beginning with
\[
F = kC,
\]
and generalized under homogeneous stiffness assumptions to
\[
\frac{dF_{\max}}{dw\,dh} = A + B C_P,
\]
where \(C_P\) is permanent crush and \(C_{\max} = C_P + \delta\). The total absorbed energy at maximum engagement is then obtained from the crush surface, with the discrete 3D formulation
\[
E = \sum_{i=1}^{N} \Delta w_i \Delta h_i
\left(
\frac{B}{2}(C_P)^2 + \frac{\tilde{A}^2}{2B} + \tilde{A}C_P
\right).
\]
In this usage, CrashShapes is a **continuous spatial description of collision damage** from which **peak force**, **absorbed energy**, and, by implication, **delta-v** and **equivalent barrier speed** can be estimated [1408.4614].

A contemporary extension of this shape-first logic appears in 3D damage localization. CrashSplat performs **3D damage segmentation by up-lifting 2D masks** into **3D Gaussian Splatting (3D-GS)**. The pipeline uses a pretrained **YOLO11** segmentation network on **CarDD** and **VehiDE**, reconstructs the scene with **COLMAP/SfM**, and then projects Gaussians into a single annotated view, retaining candidates through **Z-buffering** and a **normal-distribution-based filter over depth and opacity**. The reported self-recorded damage metrics were **IoU 65.69%** on the input view and **52.44% averaged across three views** for a scratch, **88.15%** and **87.16%** for a flat tire, and **82.41%** and **67.07%** for a broken lamp, with runtimes from **0.04 s** to **0.31 s**. On SPIn-NeRF scenes, the proposed single-view method reported mean **IoU/Acc of 79.9/96.9** [2509.23947].

These strands define three complementary regimes of crash-shape representation: **synthesis** of plausible damage geometry for interactive environments, **measurement** of crush geometry for severity estimation, and **segmentation** of damaged regions in a reconstructed 3D vehicle model [2304.05045, 1408.4614, 2509.23947].

## 4. Shape approximations for collision probability and avoidance

In automated driving, CrashShapes also denotes **shape approximations** used to evaluate safety under uncertainty. One formulation estimates the **probability of collision (POC)** by replacing exact vehicle footprints with **multiple overlapping circles** and assuming Gaussian position uncertainty. The object state is \(\boldsymbol{y} := (\boldsymbol{q}, \theta)\), and the target quantity is
\[
\textup{POC} \triangleq \mathbb{P}\{\boldsymbol{y}_o \in \tilde{\mathcal{A}}_{\text{coll}}\}.
\]
The ego rectangle of length \(l\) and width \(w\) is over-approximated by \(N_c\) circles of equal radius \(r_e\),
\[
r_e = \sqrt{\left(\frac{l}{2N_c}\right)^2 + \frac{w^2}{4}},
\qquad
d_c = 2\sqrt{r_e^2 - \frac{w^2}{4}},
\]
with the circles arranged along the longitudinal axis. For the circle-to-circle case, the anisotropic Gaussian collision integral is reduced from two dimensions to a single integral involving the error function [2405.10765].

The principal claim is computational. Average runtime per evaluation was reported as **56.340 ms** for Monte Carlo sampling, versus **0.275 ms** for the local-coordinate double integral, **0.171 ms** for the local-coordinate reduced single integral, **0.372 ms** for the global-coordinate double integral, **0.208 ms** for the global-coordinate reduced single integral, and **0.395 ms** for the polar-coordinate form. The method also supplies an approximation-error corridor:
\[
\Delta_a = \mathbb{P}\{\mathcal{A}_{coll}^{up}\} - \mathbb{P}\{\mathcal{A}_{coll}^{low}\},
\]
where the upper bound comes from a covering-circle approximation and the lower bound from inscribed circles. In this sense CrashShapes is not the crash event itself but the geometric surrogate that makes online POC computation tractable [2405.10765].

A related, broader line of work pursues less conservative collision avoidance by abandoning spherical models in favor of **ellipsoids** and combinations of **one-sheeted** and **two-sheeted hyperboloids**. The resulting 3D collision cone is constructed from planar cross-sections of the shapes. In the 2D slice, collision occurs when
\[
y < 0, \qquad \hat V_r < 0,
\]
and the 3D cone is obtained by repeating the construction over \(n\) planes containing the center-to-center vector. For a Monte Carlo study of **10,000 engagement geometries**, the relative cross-sectional area error was reported to have an upper bound of about
\[
\frac{2}{n}.
\]
This work does not use CrashShapes as a formal named framework, but it embodies the same methodological premise: the fidelity of collision reasoning depends materially on the fidelity of the shape model [2203.09037].

## 5. CrashShapes as red-teamed geometry in robotic manipulation

The most explicit formalization of CrashShapes as a named object appears in geometric red-teaming for robotic manipulation. There, CrashShapes are **object-specific, physically plausible mesh deformations that reliably cause a pre-trained manipulation policy to fail**. The policy is \(\pi:\mathcal{S}\rightarrow\mathcal{A}\), the nominal object is a mesh \(M=(V,F)\), and the deformation operator is \(D_\theta\). Red-teaming is posed as the black-box minimization
\[
\theta^*=\arg\min_{\theta\in\Theta,\; D_\theta(M)\in\mathcal{G}(M)} \mathcal{J}(\pi, D_\theta(M)),
\]
where \(\mathcal{G}(M)\) is the set of physically plausible deformations and \(\mathcal{J}\) is a task-specific performance metric measured in simulator rollouts [2509.12379].

The deformation parameterization uses a **Jacobian field-based model**. Given the source mesh \(M_0=(V_0,F_0)\), each face has a local affine Jacobian \(J_f\), and the mesh reconstruction stage solves
\[
V^{*} = \arg\min_V \|LV - \nabla^T AJ\|^2 + \lambda \|K_aV - T_a\|^2,
\]
followed by soft handle enforcement through
\[
\mathcal{L}_h = \|K_hV^* - T_h\|^2.
\]
Search is then performed by a **gradient-free black-box optimizer** with **selective perturbation**, **population size 10 candidates per iteration**, **10 optimization iterations**, Gaussian noise std **0.001 in normalized mesh units**, and perturbation of **half the parameters per iteration**. Reported red-teaming cost was about **0.5 to 4 wall-clock hours per object-policy pair on an RTX 4090** [2509.12379].

Structural validity is enforced through a **watertight, manifold mesh assumption**, **anchor constraints**, **handle constraints**, and optionally a deformation budget given by the **Smoothness Score**,
\[
\mathrm{SS}(D)=\frac{1}{M}\sum_{i=1}^{M}\|d_i\|_2,
\qquad
P_\tau(D)=sD,\quad s=\min\left\{1,\frac{\tau}{\mathrm{SS}(D)}\right\}.
\]
This guarantees \(\mathrm{SS}(P_\tau(D))\le \tau\). The paper emphasizes that even SS-constrained deformations can collapse performance, implying that very small, plausible geometry changes can expose brittle geometric assumptions in grasping, insertion, and articulated manipulation [2509.12379].

The quantitative degradations are large. For **grasping** with Contact-GraspNet, the reported **Final Drop** was **76.3%** for VLM-guided handles, **63.4%** for manual handles, and **58.3%** for VLM-guided + SS. For **articulated manipulation**, the reported **Final Drop** was **61.9%** for VLM-guided, **98.9%** for manual, and **44.7%** for manual + SS. For **insertion**, the **state-based policy** yielded **67.4%**, **73.95%**, and **60.9%**, while the **point-cloud policy** yielded **77.7%**, **71.7%**, and **43.4%**. The best ablation in grasping was **VLM-Guided + Optimization** with **76.3%**, compared with **63.3%** for **Heuristic + Gaussian** [2509.12379].

The same geometries support **blue-teaming**. PPO fine-tuning on individual CrashShapes increased state-based insertion success from **25.0%** to **87.8%** on **CS-1** and from **45.0%** to **93.8%** on **CS-2**; the point-cloud insertion policy improved from **31.3%** to **81.3%** across five CrashShapes, while nominal performance remained high. Hardware validation showed the same pattern: on an **xArm 6**, nominal insertion success was **90.0%**, falling to **22.5%** on **CS-1** and **55.0%** on **CS-2**; on a **Franka Emika Panda**, a mustard bottle dropped from **80.0%** to **30.0%**, and a screwdriver from **90.0%** to **35.0%**. In this domain, CrashShapes are simultaneously **diagnostic** and **corrective** geometries [2509.12379].

## 6. Broader shape-centric collision and fracture science

A broader literature, while not using CrashShapes as a formal named framework, treats shape as the principal observable of impact, fracture, and collapse. This suggests a deeper methodological continuity: geometry frequently serves as the compressed signature of a complex dynamical process [1005.4622, 1310.3134, 1804.11039, 1911.08634, 2206.00915].

In brittle fracture, two approaching cracks generate an **“en passant”** pattern that releases a **lenticular fragment** with aspect ratio
\[
\Gamma \equiv \frac{L}{W} \approx 2,
\]
with \(W \approx s\) and \(L \approx 2s\). The crack edge follows
\[
\left(\frac{\ell}{s}\right)=A \left(\frac{w}{s}\right)^{\alpha},
\]
with \(\langle A \rangle \approx 0.97\) and \(\langle \alpha \rangle \approx 0.49\), hence an essentially square-root trajectory. The geometric model assumes that the maximum tensile stress lies along the line connecting the two crack tips and that each crack propagates orthogonal to that direction, yielding
\[
-\frac{dy}{dx}=\frac{s}{2y}.
\]
The result is a universal lens with square-root edges across gelatin, nitrile, cork, polystyrene foam, and aluminum foil [1005.4622].

In granular impact, a collisional model explains the velocity-squared drag term by repeated inelastic collisions with force-chain clusters:
\[
F = mg - f(z) - h(z)\dot{z}^2.
\]
For triangular noses, the side contribution scales with
\[
I(s)=\frac{W}{1+s^2},
\]
and the measured data collapse gave
\[
\frac{h_0}{I[C(x)]}=B_0\approx 7.6.
\]
The same collisional asymmetry also predicts rotation, so that deceleration and rotational instability are treated as two manifestations of the same grain-scale process [1310.3134].

Asteroid-collision studies reach an analogous conclusion at planetary scale. Equal-mass, low-velocity impacts with \(U_{\rm imp}=50\text{ to }400\ {\rm m\,s^{-1}}\) and \(\theta_{\rm imp}=5^\circ\text{ to }45^\circ\) produce **bilobed, spherical, flat, elongated, and hemispherical shapes**, and the work argues that **flat shapes of asteroids larger than about 80 km are especially likely to originate from primordial similar-mass impacts** [1804.11039]. By contrast, high-resolution catastrophic-disruption simulations with about \(4\times10^6\) SPH particles per run found that collisional remnants are mainly **spherical or bilobed**, with **no remnants with \(c/a \lesssim 0.5\)**. The conclusion is that catastrophic disruptions explain most family shapes but not significantly flat asteroids, which may be **interlopers** or products of **low-velocity collisions among family members** [1911.08634].

Granular-collapse research likewise identifies shape as a control parameter. DEM simulations with square, equilateral triangular, and rectangular column cross-sections show that **edge / short-edge directions** run farther than **vertex / long-edge directions**, and that the remaining anisotropy can be collapsed by a finite-size scaling law,
\[
\tilde{\mathcal{R}} = \left(\frac{R_i^\theta}{d}\right)^{-\beta_1/\nu}
\mathcal{F}_r\left[
(\alpha_{\textrm{eff}}^\theta - \alpha_{c\infty})
\left(\frac{R_i^\theta}{d}\right)^{1/\nu}
\right],
\]
with fitted parameters \(\nu = 1.39 \pm 0.14\) and \(\beta_1 = 0.28 \pm 0.04\). The shape effect is thus interpreted as a finite-size effect in disguise [2206.00915].

Across these otherwise disparate domains, the shared pattern is clear. Shape is not merely a visualization of a collision outcome; it is often the **state variable**, the **inference target**, the **control surrogate**, or the **failure-inducing perturbation**. That continuity explains why the label CrashShapes can plausibly encompass scenario geometry, damage surfaces, safety approximations, and adversarial deformations within a single encyclopedic category.

Source: https://www.emergentmind.com/topics/crashshapes