* External authors




Planetary Environment Prediction Using Generative Modeling

Shrijit Singh*

Shreyansh Daftry*

Roberto Capobianco

* External authors

AIAA SciTech Forum 2022



Planetary rovers have a limited sensory horizon and operate in environments where limited information about the surrounding terrain is available. The rough and unknown nature of the terrain in planetary environments potentially leads to scenarios where the rover gets stuck
and has to replan its path frequently to escape such situations. For avoiding such scenarios,
we need to exploit spatial knowledge of the environment beyond the rover’s sensor horizon.
The solutions presented by existing approaches are limited to indoor environments which are
structured. Predicting spatial knowledge for outdoor environments, particularly planetary
environments, has not be done before. We attempt to solve planetary environment prediction
by exploiting generative learning to (1) learn the distribution of spatial landmarks like rocks
and craters which the rover encounter on the planetary surface during exploration and (2)
predict spatial landmarks beyond the sensor horizon. We aim to utilize the proposed approach
of environment prediction to improve path planning and decision-making processes needed for
safe planetary navigation.

Related Publications

Outracing Champion Gran Turismo Drivers with Deep Reinforcement Learning

Nature, 2022
Pete Wurman, Samuel Barrett, Kenta Kawamoto, James MacGlashan, Kaushik Subramanian, Thomas J. Walsh, Roberto Capobianco, Alisa Devlic, Franziska Eckert, Florian Fuchs, Leilani Gilpin, Piyush Khandelwal, Varun Kompella, Hao Chih Lin, Patrick MacAlpine, Declan Oller, Takuma Seno, Craig Sherstan, Michael D. Thomure, Houmehr Aghabozorgi, Leon Barrett, Rory Douglas, Dion Whitehead Amago, Peter Dürr, Peter Stone, Michael Spranger, Hiroaki Kitano

Many potential applications of artificial intelligence involve making real-time decisions in physical systems while interacting with humans. Automobile racing represents an extreme example of these conditions; drivers must execute complex tactical manoeuvres to pass or block…

Tafl-ES: Exploring Evolution Strategies for Asymmetrical Board Games

AIxIA, 2021
Roberto Gallotta*, Roberto Capobianco

NeuroEvolution Strategies (NES) are a subclass of Evolution Strategies (ES). While their application to games and board games have been studied in the past [11], current state of the art in most of the games is still held by classic RL models, such as AlphaGo Zero [16]. This…

Exploration-Intensive Distractors: Two Environment Proposals and a Benchmarking

AIxIA, 2021
Jim Martin Catacora Ocaña*, Roberto Capobianco, Daniele Nardi*

Sparse-reward environments are famously challenging for deep reinforcement learning (DRL) algorithms. Yet, the prospect of solving intrinsically sparse tasks in an end-to-end fashion without any extra reward engineering is highly appealing. Such aspiration has recently led t…


Shape the Future of AI with Sony AI

We want to hear from those of you who have a strong desire
to shape the future of AI.