AI-MIX: Using Automated Planning to Steer Human Workers Towards Better Crowdsourced Plans

Abstract

One subclass of human computation applications are those directed at tasks that involve planning (e.g. tour planning) and scheduling (e.g. conference scheduling). Interestingly, work on these systems shows that even primitive forms of automated oversight on the human contributors helps in significantly improving the effectiveness of the humans/crowd. In this paper, we argue that the automated oversight used in these systems can be viewed as a primitive automated planner, and that there are several opportunities for more sophisticated automated planning in effectively steering the crowd. Straightforward adaptation of current planning technology is however hampered by the mismatch between the capabilities of human workers and automated planners. We identify and partially address two important challenges that need to be overcome before such adaptation of planning technology can occur: (i) interpreting inputs of the human workers (and the requester) and (ii) steering or critiquing plans produced by the human workers, armed only with incomplete domain and preference models. To these ends, we describe the implementation of AI-MIX, a tour plan generation system that uses automated checks and alerts to improve the quality of plans created by human workers; and present a preliminary evaluation of the effectiveness of steering provided by automated planning.

Analysis and Research Based on the Crowdsourcing Corpus System in Guangdong-Hong Kong-Macao Greater Bay Area (GBA)

“…(4) Application in the field of transportation: Yang [8] applied crowdsourcing to traffic monitoring, and proposed the concept of collecting very large-scale sensory data with a large number of personal smartphones, which subverts the traditional realtime road condition information collection technology. Manikonda et al [9] developed a travel plan generation system named AI-MIX. (5) Applications in scientific research: the domestic scholar Zhang [10] first proposed the concept of scientific research crowdsourcing, that is, gather the wisdom of global researchers to collaborate on scientific research and solve scientific research problems together.…”

Collaborative Planning with Encoding of Users' High-Level Strategies

“…Other systems have led to support for certain low-level interactions with automated planners, such as ordering goals for expansion, selecting which actions to apply and choosing instantiations for planning variables (Tate 1994;Wilkins 1999). Systems such as AI-MIX (Manikonda et al 2014) and RADAR (Vadlamudi et al 2016) help users compose plans while the system performs constraint checking and offers constructive critiques (e.g., suggested actions that users can either accept or reject). AI-MIX also introduced a planning system that steers users' planning process to better mimic a database of plans collected from a crowd.…”

Crowdsourced Action-Model Acquisition for Planning

“…Dai et al (Dai et al 2013) designed AI agents to obtain cost-quality tradeoff based on Bayesian learning and inference. Talamadupula et al (Talamadupula et al 2013;Manikonda et al 2014) presented a general framework that foregrounds the potential roles of automated planners in crowd-planning. Cenamor et al (Cenamor, de la Rosa, and Borrajo 2013) proposed an initial idea of attaining information from traveling social network to build tourist plans.…”