Adaptive advice in automobile climate control systems

Ariel Rosenfeld, Amos Azaria, Sarit Kraus, Claudia V. Goldman, Omer Tsimhoni

Research output: Contribution to journalArticlepeer-review


Copyright © 2015, International Foundation for Autonomous Agents and Multiagent Systems. Reducing an automobile's energy consumption will lower its dependency on fossil fuel and extend the travel range of electric vehicles. Automobile Climate Control Systems (CCS) are known to be heavy energy consumers. To help reduce CCS energy consumption, this paper presents an adaptive automated agent, MDP Agent for Climate control Systems (MACS), which provides drivers with advice as to how to set their CCS. First, we present a model which has 78% accuracy in predicting drivers' reactions to different advice in different situations. Using the prediction model, we designed a Markov Decision Process which solution provided the advising policy for MACS. Through empirical evaluation using an electric car, with 83 human subjects, we show that MACS successfully reduced the energy consumption of the subjects by 33% compared to subjects who were not equipped with MACS. MACS also outperformed the state-of-the-art Social agent for Advice Provision (SAP).
Original languageEnglish
Pages (from-to)543-551
Number of pages8
JournalProceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS
StatePublished - 1 Jan 2015


Dive into the research topics of 'Adaptive advice in automobile climate control systems'. Together they form a unique fingerprint.

Cite this