IBM Research-Tokyo

IBM scientists demo social simulator

Share this post:

Screen shot of shopping mall simulation.

Screen shot of shopping mall simulation.

Real life is taking a step closer to The Sims video game series.

This week at SuperComputing 17 in Denver, Colorado, the Japan Science and Technology Agency (JST) is introducing series of demos, including new research from IBM scientists in Japan which can simulate social situations such as shopping at the mall or an emergency evacuation.

Our social systems are complex. Just look at how we behave and interact among each other seems as complicated and dynamic as nature. By unfolding the dynamics of economic-social systems, we can better understand the complex dynamics of our social systems, but we first need to find ways to better understand phenomena at a micro-level where many heterogeneous autonomous agents, such as myself, are considering and acting under the influence of the environment and others.

We call this work open source social simulation framework XASDI, which stands for X10-based Agent Simulation on Distributed Infrastructure and it can run on anything from a desktop to a cloud to a supercomputer. By using this framework, we can develop various social simulation applications to help us make better decision for urban planning and other decisions that we need to make for the society as a whole.

For example, during the development of XASDI, we simulated where people gather at a shopping mall to determine where tenants should be placed in the mall or where to put exits and public seating to reduce congestion.

Another way we could apply the simulator is for emergencies, to help people evacuate disaster areas safely and quickly.

The butterfly effect may bring us an unexpected result due to the complexity our society holds. Yet, we need to do our best to try and understand beyond our comprehension as much as possible for better decision making. I hope XASDI is used by developers and designers to create apps to serve such needs.

This work is funded by the Japan Science and Technology Agency (JST)’s Core Research for Evolutionary Science and Technology (CREST).

Save

Save

Save

Save

Save

More IBM Research-Tokyo stories

Could AI Help People Change Their Behaviour?

An open-source AI algorithm to help people change their behaviour, based on an ontology developed by behavioural scientists at University College London.

Continue reading

IBM’s AI Experiments Hub Puts Cutting-Edge Technology in Your Hands

IBM Research launches new AI Experiments hub featuring prototypes of tools and resources that will unleash the power of AI.

Continue reading

Efficient Deep Learning Training on the Cloud with Small Files

Here I describe an approach to efficiently train deep learning models on machine learning cloud platforms (e.g., IBM Watson Machine Learning) when the training dataset consists of a large number of small files (e.g., JPEG format) and is stored in an object store like IBM Cloud Object Storage (COS). As an example, I train a […]

Continue reading