Adaptive Advice in Automobile Climate Control 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 ad- vising 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).

[1]  Amos Azaria,et al.  Advice Provision for Energy Saving in Automobile Climate-Control System , 2015, AI Mag..

[2]  Jaap Ham,et al.  A robot that says “bad!”: Using negative and positive social feedback from a robotic agent to save energy , 2009, 2009 4th ACM/IEEE International Conference on Human-Robot Interaction (HRI).

[3]  Stéphane Ploix,et al.  A multi-agent home automation system for power management , 2006, ICINCO-ICSO.

[4]  Michael A. Regan,et al.  Driver distraction: A review of the literature , 2003 .

[5]  Juho Hamari,et al.  Do Persuasive Technologies Persuade? - A Review of Empirical Studies , 2014, PERSUASIVE.

[6]  B. J. Fogg,et al.  Persuasive technology: using computers to change what we think and do , 2002, UBIQ.

[7]  Grant Lovellette,et al.  Will Electric Cars Transform The U . S . Vehicle Market ? An Analysis of The Key Determinants , 2011 .

[8]  M. Rabin,et al.  A Model of Reference-Dependent Preferences , 2006 .

[9]  Katja Kircher,et al.  Driver distraction : a review of the literature , 2007 .

[10]  Anind K. Dey,et al.  Navigate like a cabbie: probabilistic reasoning from observed context-aware behavior , 2008, UbiComp.

[11]  Amos Azaria,et al.  Strategic advice provision in repeated human-agent interactions , 2012, Autonomous Agents and Multi-Agent Systems.

[12]  Milind Tambe,et al.  Human-Building Interaction for Energy Conservation in Office Buildings , 2012 .

[13]  S. Karjalainen,et al.  Thermal comfort and gender: a literature review. , 2012, Indoor air.

[14]  Amos Azaria,et al.  Strategic Information Disclosure to People with Multiple Alternatives , 2011, AAAI.

[15]  Milind Tambe,et al.  SAVES: a sustainable multiagent application to conserve building energy considering occupants , 2012, AAMAS.

[16]  Eric Horvitz,et al.  Trip Router with Individualized Preferences (TRIP): Incorporating Personalization into Route Planning , 2006, AAAI.

[17]  Guy Shani,et al.  An MDP-Based Recommender System , 2002, J. Mach. Learn. Res..

[18]  U. Rieder,et al.  Markov Decision Processes , 2010 .

[19]  Jeffrey Gonder,et al.  Analyzing Vehicle Fuel Saving Opportunities through Intelligent Driver Feedback , 2012 .

[20]  Harry Zhang,et al.  Traffic Advisories Based on Route Prediction , 2007 .

[21]  Eric Horvitz,et al.  Predestination: Inferring Destinations from Partial Trajectories , 2006, UbiComp.

[22]  Suleman Shahid,et al.  iParrot: Towards Designing a Persuasive Agent for Energy Conservation , 2007, PERSUASIVE.

[23]  James A. Landay,et al.  UbiGreen: investigating a mobile tool for tracking and supporting green transportation habits , 2009, CHI.

[24]  James A. Landay,et al.  The design of eco-feedback technology , 2010, CHI.

[25]  Harri Oinas-Kukkonen,et al.  A foundation for the study of behavior change support systems , 2012, Personal and Ubiquitous Computing.

[26]  Sarit Kraus,et al.  How to Change a Group's Collective Decision? , 2013, IJCAI.