The Dynamic Pickup and Delivery Problem (DPDP) is an essential problem within the logistics domain. So far, research on this problem has mainly focused on using artificial data which fails to reflect the complexity of real-world problems. With this competition, we hope to promote the research and development of techniques applicable to such problems, by building the competition around a dataset generated from real business scenarios of Huawei Technologies Ltd.
In this competition, participants are invited to develop automatic reinforcement learning solutions to the dynamic job shop scheduling problem (DJSSP). The solutions are expected to automatically train promising agents on a distribution of DJSSP tasks. After a feedback phase where solutions can be developed and fine-tuned with daily feedback, those that perform best on a set of five unseen tasks win the competition.
On the way towards a sustainable future and following up the
L2RPN 2020 NeurIPS competition, this competition aims at unleashing the power of
artificial intelligence even further for our real-world
industrial application: controlling electricity power
transmission in real-time and moving closer to truly “smart”
grids using underutilized flexibilities. In 2020,
participants were asked to develop an agent to be robust to
unexpected events and keep delivering reliable electricity
everywhere even in difficult circumstances.
In this competition, participants, while dealing with a higher penetration of renewable energy, will be asked in addition to design trustworthy agents that are able to communicate when they are in trouble, especially when they might fail. This will more concretely lead the path towards an AI assistant for human operators, who will still be responsible for managing the grid, rather than a mere blackbox agent. Join us for this Augmented Intelligence competition!
This challenge tackles a key problem in the transportation world: How to efficiently manage dense traffic on complex railway networks? This is a real-world problem faced by many transportation and logistics companies around the world such as the Swiss Federal Railways and Deutsche Bahn. Your contribution may shape the way modern traffic management systems are implemented, not only in railway but also in other areas of transportation and logistics!
In the field of autonomous driving, it is a consensus in
both academia and industry that behavior prediction (e.g.,
trajectories, actions, intentions) is one of the most
challenging problems blocking the realization of full
autonomy. The problem cannot be solved without support from
real-world motion data containing highly interactive
behavior, as well as proper evaluation metrics and
approaches for a variety of prediction algorithms based on
The Mechanical Systems Control Laboratory (MSC Lab) at UC Berkeley has constructed an INTERnational, Adversarial and Cooperative moTION dataset (INTERACTION dataset) with collaborators from KIT and MINES ParisTech. It accurately recovers large amounts of highly interactive motions of road users (e.g., vehicles, pedestrians) in a variety of driving scenarios from different countries. To expedite research and inspire discussions on the evaluation of prediction models/algorithms, we present the INTERACTION-Dataset-based PREdicTion Challenge (INTERPRET). This is a step towards the construction of effective and valuable predictors for the development of autonomous driving.
Read more about the rich history of competitions at ICAPS here, including more than two decades of the International Planning Competition. This year we continue this tradition and bring to you a host of challenges based on real world data with help from our partners across industry and academia. We hope this keeps you busy during the summer as we await a slightly delayed ICAPS in Fall! 🤓
Got questions? Please reach out to the ICAPS 2021 Competition Chairs.