AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

Causal Navigation by Continuous-time Neural Networks

NeurIPS 2021 · Probabilistic and scientific modeling › Dynamical systems · approach: Latent-space control and planning · 25 citations (OpenAlex)

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 changedWhereMeasuredEffect
use NCP (liquid time-constant, causal CT) instead of LSTMdrone policy · Static target, clearclosed-loop success rate: 24% -> 48%Helped
use NCP instead of ODE-RNN (generic neural ODE)drone policy · Chasing, clearclosed-loop success rate: 52% -> 78%Helped
use NCP instead of LSTMdrone policy · Heavy rain static targetclosed-loop success rate: 4% -> 60%Helped
use NCP instead of CT-GRUdrone policy · Hiking, clearclosed-loop success rate: 0% -> 30%Helped
add recurrent memory instead of single-frame CNNdrone policy · Static target occlusionclosed-loop success rate: 4% -> 32%Helped
NCP vs LSTM under fog in chasingdrone policy · Chasing, fogclosed-loop success rate: 62% -> 52%Hurt
NCP vs CT-GRU in light rain static targetdrone policy · Static target, light rainclosed-loop success rate: 60% -> 52%Hurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy