AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

[Re] Differentiable Spatial Planning using Transformers

Rohit Ranjan, Himadri Bhakta, Animesh Jha, Parv Maheshwari

NeurIPS 2022 · Architectures and efficiency › Attention and transformers · approach: Transformer expressivity and learnability

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (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
increase CNN Encoder layers from 2 to 4 (ablation)SPT · M=15accuracy: 84.40 -> 84.88Improved
increase CNN Encoder layers from 2 to 8 (ablation)SPT · M=15accuracy: 84.40 -> 84.90Improved
reduce d_model from 64 to 32 (ablation)SPT · M=15accuracy: 84.40 -> 84.76Improved
increase d_model from 64 to 128 (ablation)SPT · M=15accuracy: 84.40 -> 85.00Improved
increase obstacle range from N(0,5) to N(0,10) (ablation)SPT · M=15accuracy: 84.40 -> 84.31Hurt
increase obstacle range from N(0,5) to N(0,15) (ablation)SPT · M=15accuracy: 84.40 -> 84.67Improved
reduce attention heads from 8 to 4 (ablation)SPT · M=15accuracy: 84.40 -> 84.65Improved
increase attention heads from 8 to 16 (ablation)SPT · M=15accuracy: 84.40 -> 84.24Hurt
increase Transformer layers from 5 to 8 (ablation)SPT · M=15accuracy: 84.40 -> 84.96Improved
increase Transformer layers from 5 to 12 (ablation)SPT · M=15accuracy: 84.40 -> 52.33Hurt
combine CNN layers=8, d_model=128, n_heads=4, and Transformer layers=8 (ablation)SPT · M=15accuracy: 84.40 -> 85.14; 0.87%Improved
use SPT instead of GPPNSpatial planning · Navigation M=15, M=30, M=50; Manipulation M=18, M=36; Overallaccuracy: 97.10 -> 99.07; 96.17 -> 99.56; 91.97 -> 99.42; 89.06 -> 99.24; 87.23 -> 99.78; 92.31 -> 99.41Improved

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