AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

AcoustoReinforce: Multi-Particle Acoustophoretic Path Planning with Deep Reinforcement Learning

Pengyuan Wei, Giorgos Christopoulos, Zhouyang Shen, Jincheng Wang, Joshua Mukherjee, Ryuji Hirayama, Sriram Subramanian, Prateek Mittal

AAAI 2026 · Reinforcement learning › Visual and representation RL · approach: Dexterous manipulation transfer · 1 citations (OpenAlex)

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
use AcoustoReinforce instead of S2M2multi-particle path planning · Simulation, 10 particlessuccess rate: 0.8920 -> 0.9830Improved
use AcoustoReinforce instead of CBSmulti-particle path planning · Simulation, 10 particlessuccess rate: 0.9370 -> 0.9830Improved
use AcoustoReinforce instead of S2M2 and CBS at low particle countsmulti-particle path planning · Real levitator, 4 particles, Vmax 0.05 to 0.15 m/ssuccess rate: 1.000 for all threeNo clear effect
use AcoustoReinforce instead of S2M2multi-particle path planning · Real levitator, 8 particles, Vmax 0.20 m/ssuccess rate: 0.2000 -> 0.4600Improved
use AcoustoReinforce instead of CBSmulti-particle path planning · Real levitator, 10 particles, Vmax 0.20 m/ssuccess rate: 0.0000 for all methodsNo clear effect
use AcoustoReinforce instead of CBSmulti-particle path planning · Real levitator, 6 particles, Vmax 0.10 m/ssuccess rate: 0.9000 -> 0.9400Improved
use AcoustoReinforce instead of CBSmulti-particle path planning · Real levitator, 6 particles, Vmax 0.05 m/ssuccess rate: 1.000 -> 0.9900Hurt
use AcoustoReinforce instead of S2M2 and CBSmulti-particle path planning · Gor'kov potential at turning pointspotential (lower is better): reductions of up to 20%Improved
add turning-point Gor'kov optimization to the policy (ablation)AcoustoReinforce · Gor'kov potential at turning pointspotential (lower is better): policy alone improves by approximately 5%Improved
increase particle count from 4 to 10 on difference between planners in Gor'kov potentialAcoustoReinforce · Gor'kov potential at turning pointspotential: differences decrease with more particlesMixed
increase Vmax from 0.05 to 0.20 m/sAcoustoReinforce · Real levitator, 8 particlessuccess rate: 0.9900 -> 0.4600Hurt

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