Skip to content

Antimony-contact MoS2 FET gas sensors for reinforcement-learning–driven hazard perception at room temperature

Sep 2026 · Microsystems & Nanoengineering · 63 references
2D Materials and Applications

Abstract

Two-dimensional van der Waals semiconductors promise low-power chemical perception at room temperature, yet contact-limited on-currents and slow recovery impede closed-loop decision making in hazardous environments. Here we propose antimony (Sb)-contact two-dimensional (2D) monolayer MoS 2 field-effect transistors (FETs) that leverage contact engineering to boost on-current and charge-transfer gas response for room temperature detection and enable electrically programmable recovery via pre-bias pulses that actively accelerate desorption and baseline restoration. The Sb-contact MoS 2 FETs show unprecedented ppb gas response (363,600% at 500 ppb NO 2 ) and rapid, repeatable room temperature recovery with ultra-low energy consumption (42 pJ, representing the intrinsic energy efficiency of the sensing front-end), serving as a proof-of-concept for the front-end of a safety-constrained reinforcement-learning (RL) stack that detects leak sources and plans low-risk escape path in turbulent interiors. We cast joint seek-and-escape as a single constrained Markov decision process informed by real-time transduction features fused with thermal–flow cues; the learned policy achieves earlier detection, lower cumulative exposure, and shorter safe-egress paths than heuristic baselines in computational fluid dynamics (CFD)-validated simulations and chamber trials. By uniting contact-engineered 2D transducers with risk-aware RL, this work advances room temperature chemical sensing from passive monitoring to closed-loop action.

View source

Similar papers

#machine learning Review Open access Oct 2014

Software development in startup companies: A systematic mapping study

The results indicate that software engineering work practices are chosen opportunistically, adapted and configured to provide value under the constrains imposed by the startup context.

Nicolò Paternoster, Carmine Giardino, M. Unterkalmsteiner et al. · 394 citations · ⚡54
#machine learning Review Open access Jun 2014

Why Early-Stage Software Startups Fail: A Behavioral Framework

This state-of-practice investigation was performed using a literature review followed by a multiple-case study approach and presents how inconsistency between managerial strategies and execution can lead to failure by means of a behavioral framework.

Carmine Giardino, Xiaofeng Wang, P. Abrahamsson · 175 citations · ⚡19
#machine learning Review Open access Oct 2016

“Failures” to be celebrated: an analysis of major pivots of software startups

This study conducts a case survey study based on the secondary data of the major pivots happened in 49 software startups, and demonstrates that customer need pivot is the most common among all pivot types.

Sohaib Shahid Bajwa, Xiaofeng Wang, Anh Nguyen-Duc et al. · 127 citations · ⚡15
#machine learning Review Open access May 2016

Key Challenges in Software Startups Across Life Cycle Stages

It is found that what perceived as biggest challenges by software startups do vary across different life cycle stages, even though its significance decreases when the learning focuses of the startups move from problem to solution and their products mature.

Xiaofeng Wang, Henry Edison, Sohaib Shahid Bajwa et al. · 62 citations · ⚡6

Related blog posts

Microsoft Research Blog Oct 12, 2026

Simulating student learning for better AI tutoring

StudentSim is a research system for evaluating and improving AI tutoring tools before they are tested with learners. It models how individuals may engage with tutors, giving feedback to improve tutor performance across subjects like chess, writing, and mathematics. The post Simulating student learning for better AI tutoring appeared first on Microsoft Research.

MIT News · Artificial Intelligence Oct 7, 2026

Discovering the value of humanistic inquiry

Students in MIT’s Concourse program delve deeply into the human condition, debate challenging questions, and learn to develop judgment about issues that can’t be quantified.

Microsoft Research Blog Oct 7, 2026

Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses

Training AI agents with reinforcement learning can be challenging because their tools, context, and decision-making are managed by complex frameworks. Agent Lightning connects existing agents to RL training, making it easier to improve them without rebuilding them. The post Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.