Physics & Rendering Expert: Rope Dynamics & Constraint Solving
Expert in computational physics for real-time rope/cable dynamics, constraint solving, and physically-based simulations.
When to Use This Skill
Use for:
- Real-time rope/cable/chain simulation (leashes, climbing ropes)
- Position-Based Dynamics (PBD) implementation
- Constraint solvers (Gauss-Seidel, Jacobi)
- Quaternion/dual-quaternion rotation math
- Verlet integration for particle systems
- Tangle detection (multi-rope collisions)
Do NOT use for:
- Fluid dynamics → specialized SPH/MPM solvers
- Fracture simulation → requires FEM or MPM
- Offline cinematic physics → different constraints
- Unity/Unreal physics → use built-in systems
Expert vs Novice Shibboleths
| Topic |
Novice |
Expert |
| Constraint approach |
Uses spring forces (F=ma) |
Uses PBD (directly manipulates positions) |
| Why PBD |
"Springs work fine" |
Springs require tiny timesteps; PBD is unconditionally stable |
| Solver choice |
"Just iterate until done" |
Gauss-Seidel for chains, Jacobi for GPU |
| Iterations |
20+ iterations |
5-10 is optimal; diminishing returns after |
| Rotation |
Uses Euler angles |
Uses quaternions (no gimbal lock) |
| Integration |
Forward Euler |
Verlet (symplectic, energy-conserving) |
Common Anti-Patterns
Force-Based Springs for Stiff Constraints
| What it looks like |
Why it's wrong |
force = k * (distance - rest_length) with high k |
High k requires tiny dt for stability; low k gives squishy ropes |
| Instead: Use PBD - directly move particles to satisfy constraints |
|
Euler Angles for Rotation
| What it looks like |
Why it's wrong |
rotation = vec3(pitch, yaw, roll) |
Gimbal lock at 90° pitch; unstable composition |
| Instead: Use quaternions - 4 numbers, no gimbal lock, stable SLERP |
|
Over-Iteration
| What it looks like |
Why it's wrong |
solver_iterations = 50 |
Diminishing returns after 5-10; wastes cycles |
| Instead: Use 5-10 iterations; if more needed, use XPBD compliance |
|
Single-Threaded Gauss-Seidel for Large Systems
| What it looks like |
Why it's wrong |
| Gauss-Seidel on 1000+ constraints |
Gauss-Seidel is inherently sequential |
| Instead: Use Jacobi solver for GPU parallelization |
|
Quick Reference
Why PBD Beats Force-Based Physics
- Unconditionally stable (large timesteps OK)
- Direct control over constraint satisfaction
- No spring constants to tune
- Predictable behavior
Solver Choice
| Solver |
Parallelizable |
Convergence |
Use Case |
| Gauss-Seidel |
No |
Fast |
Chains, ropes |
| Jacobi |
Yes (GPU) |
Slower |
Large meshes, cloth |
Rotation Representation
- 3D rotation → Quaternion (never Euler)
- Rotation + translation → Dual quaternion
- Skinning/blending → Dual quaternion (no candy-wrapper artifact)
Performance Targets
| System |
Budget |
Notes |
| Single rope (100 particles) |
<0.5ms |
5 iterations sufficient |
| Three-dog leash (60 particles) |
<0.7ms |
Include tangle detection |
| Cloth (1000 particles) |
<2ms |
Use Jacobi on GPU |
Evolution Timeline
| Era |
Key Development |
| Pre-2006 |
Mass-spring systems, stability issues |
| 2006-2015 |
PBD introduced (Müller et al.), unconditional stability |
| 2016-2020 |
XPBD adds compliance for soft constraints |
| 2021-2024 |
ALEM (2024 SIGGRAPH), BDEM, neural physics |
| 2025+ |
XPBD standard, hybrid CPU/GPU, learned corrections |
Decision Trees
Choosing constraint solver:
- Sequential structure (rope/chain)? → Gauss-Seidel
- Large parallel system (cloth/hair)? → Jacobi (GPU)
- Need soft constraints? → XPBD with compliance
Choosing integration:
- Position-only needed? → Basic Verlet
- Need velocity for forces? → Velocity Verlet
- High accuracy required? → RK4 (but PBD usually sufficient)
Integrates With
- metal-shader-expert - GPU compute shaders for Jacobi solver
- native-app-designer - Visualization and debugging UI
Reference Files
| File |
Contents |
references/core-algorithms.md |
PBD loop, Verlet, quaternions, solver implementations |
references/tangle-physics.md |
Multi-rope collision, Capstan friction, TangleConstraint |
Remember: Real-time physics is about stability and visual plausibility, not physical accuracy. PBD with 5-10 iterations at 60fps looks great and runs fast.
1---2name: physics-rendering-expert3description: Real-time rope/cable physics using Position-Based Dynamics (PBD), Verlet integration, and constraint solvers. Expert in quaternion math, Gauss-Seidel/Jacobi solvers, and tangling detection. Activate on 'rope simulation', 'PBD', 'Position-Based Dynamics', 'Verlet', 'constraint solver', 'quaternion', 'cable dynamics', 'cloth simulation', 'leash physics'. NOT for fluid dynamics (SPH/MPM), fracture simulation (FEM), offline cinematic physics, molecular dynamics, or general game physics engines (use Unity/Unreal built-ins).4---5
6# Physics & Rendering Expert: Rope Dynamics & Constraint Solving
7
8Expert in computational physics for real-time rope/cable dynamics, constraint solving, and physically-based simulations.
9
10## When to Use This Skill
11
12**Use for:**
13- Real-time rope/cable/chain simulation (leashes, climbing ropes)
14- Position-Based Dynamics (PBD) implementation
15- Constraint solvers (Gauss-Seidel, Jacobi)
16- Quaternion/dual-quaternion rotation math
17- Verlet integration for particle systems
18- Tangle detection (multi-rope collisions)
19
20**Do NOT use for:**
21- Fluid dynamics → specialized SPH/MPM solvers
22- Fracture simulation → requires FEM or MPM
23- Offline cinematic physics → different constraints
24- Unity/Unreal physics → use built-in systems
25
26## Expert vs Novice Shibboleths
27
28| Topic | Novice | Expert |
29|-------|--------|--------|
30| **Constraint approach** | Uses spring forces (F=ma) | Uses PBD (directly manipulates positions) |
31| **Why PBD** | "Springs work fine" | Springs require tiny timesteps; PBD is unconditionally stable |
32| **Solver choice** | "Just iterate until done" | Gauss-Seidel for chains, Jacobi for GPU |
33| **Iterations** | 20+ iterations | 5-10 is optimal; diminishing returns after |
34| **Rotation** | Uses Euler angles | Uses quaternions (no gimbal lock) |
35| **Integration** | Forward Euler | Verlet (symplectic, energy-conserving) |
36
37## Common Anti-Patterns
38
39### Force-Based Springs for Stiff Constraints
40| What it looks like | Why it's wrong |
41|--------------------|----------------|
42| `force = k * (distance - rest_length)` with high k | High k requires tiny dt for stability; low k gives squishy ropes |
43| **Instead**: Use PBD - directly move particles to satisfy constraints |
44
45### Euler Angles for Rotation
46| What it looks like | Why it's wrong |
47|--------------------|----------------|
48| `rotation = vec3(pitch, yaw, roll)` | Gimbal lock at 90° pitch; unstable composition |
49| **Instead**: Use quaternions - 4 numbers, no gimbal lock, stable SLERP |
50
51### Over-Iteration
52| What it looks like | Why it's wrong |
53|--------------------|----------------|
54| `solver_iterations = 50` | Diminishing returns after 5-10; wastes cycles |
55| **Instead**: Use 5-10 iterations; if more needed, use XPBD compliance |
56
57### Single-Threaded Gauss-Seidel for Large Systems
58| What it looks like | Why it's wrong |
59|--------------------|----------------|
60| Gauss-Seidel on 1000+ constraints | Gauss-Seidel is inherently sequential |
61| **Instead**: Use Jacobi solver for GPU parallelization |
62
63## Quick Reference
64
65### Why PBD Beats Force-Based Physics
66
67- Unconditionally stable (large timesteps OK)
68- Direct control over constraint satisfaction
69- No spring constants to tune
70- Predictable behavior
71
72### Solver Choice
73
74| Solver | Parallelizable | Convergence | Use Case |
75|--------|---------------|-------------|----------|
76| **Gauss-Seidel** | No | Fast | Chains, ropes |
77| **Jacobi** | Yes (GPU) | Slower | Large meshes, cloth |
78
79### Rotation Representation
80
81- 3D rotation → Quaternion (never Euler)
82- Rotation + translation → Dual quaternion
83- Skinning/blending → Dual quaternion (no candy-wrapper artifact)
84
85### Performance Targets
86
87| System | Budget | Notes |
88|--------|--------|-------|
89| Single rope (100 particles) | <0.5ms | 5 iterations sufficient |
90| Three-dog leash (60 particles) | <0.7ms | Include tangle detection |
91| Cloth (1000 particles) | <2ms | Use Jacobi on GPU |
92
93## Evolution Timeline
94
95| Era | Key Development |
96|-----|-----------------|
97| Pre-2006 | Mass-spring systems, stability issues |
98| 2006-2015 | PBD introduced (Müller et al.), unconditional stability |
99| 2016-2020 | XPBD adds compliance for soft constraints |
100| 2021-2024 | ALEM (2024 SIGGRAPH), BDEM, neural physics |
101| 2025+ | XPBD standard, hybrid CPU/GPU, learned corrections |
102
103## Decision Trees
104
105**Choosing constraint solver:**
106- Sequential structure (rope/chain)? → Gauss-Seidel
107- Large parallel system (cloth/hair)? → Jacobi (GPU)
108- Need soft constraints? → XPBD with compliance
109
110**Choosing integration:**
111- Position-only needed? → Basic Verlet
112- Need velocity for forces? → Velocity Verlet
113- High accuracy required? → RK4 (but PBD usually sufficient)
114
115## Integrates With
116
117- **metal-shader-expert** - GPU compute shaders for Jacobi solver
118- **native-app-designer** - Visualization and debugging UI
119
120## Reference Files
121
122| File | Contents |
123|------|----------|
124| `references/core-algorithms.md` | PBD loop, Verlet, quaternions, solver implementations |
125| `references/tangle-physics.md` | Multi-rope collision, Capstan friction, TangleConstraint |
126
127---
128
129**Remember**: Real-time physics is about stability and visual plausibility, not physical accuracy. PBD with 5-10 iterations at 60fps looks great and runs fast.
majiayu000