Research map / Probabilistic and scientific modeling / Dynamical systems
Learning-In-The-Loop Optimization: End-To-End Control And Co-Design Of Soft Robots Through Learned Deep Latent Representations
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use learned VAE latent observer instead of k-means clustering observer | soft robot controller · 2D Biped, Elephant, Bunny | loss vs optimization iteration / reliability | Helped |
| use VAE observer instead of k-means clustering | soft robot controller · 2D Arm | loss vs optimization iteration | Mixed |
| use VAE observer instead of k-means clustering | soft robot controller · 2D Elephant | loss vs optimization iteration | Helped |
| use a variational autoencoder instead of a non-variational autoencoder (ablation) | LITL observer · soft robot control | control optimization success | Helped |
| add experience replay buffer for autoencoder training (ablation) | LITL · 2D Arm | control optimization success | Helped |
| continuously retrain autoencoder instead of one-shot training on initial motion (ablation) | LITL · 2D Arm | control optimization success | Helped |
| alternate learning and optimization instead of training simultaneously (ablation) | LITL · soft robot control | avoiding local minima | Helped |
| retrain autoencoder, then perform one optimization step (ablation) | LITL · 2D Biped locomotion | distance traveled change: −1.08 × 10−2 (retrain 1), 3.56 × 10−2 (retrain 4) | No clear effect |
Closest papers by meaning
- DittoGym: Learning to Control Soft Shape-Shifting Robots (ICLR 2024 · similarity 0.87)
- Neural Contractive Dynamical Systems (ICLR 2024 · similarity 0.86)
- MorphVAE: Advancing Morphological Design of Voxel-Based Soft Robots with Variational Autoencoders (AAAI 2024 · similarity 0.85)
- DeformGen: Dynamics-Based Topology Augmentation for Deformable Manipulation Policy Learning (NeurIPS 2026 · similarity 0.85)
- Input-to-State Stable Coupled Oscillator Networks for Closed-form Model-based Control in Latent Space (NeurIPS 2024 · similarity 0.84)
- DynaFLIP: Rethinking Robotics Perception via Tri-Modal-Dynamics Guided Representation (NeurIPS 2026 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.