Robot Learning

Neural Control Barrier Functions for Safe Navigation

Autonomous robot navigation can be particularly demanding, especially when the surrounding environment is not known and safety of the robot is crucial. This work relates to the synthesis of Control Barrier Functions (CBFs) through data for safe navigation in unknown environments. A novel methodology to jointly learn CBFs and corresponding safe controllers, in simulation, inspired by the State Dependent Riccati Equation (SDRE) is proposed.

ORACLE Library of Deep Learning-based Safe Navigation Methods: Indicative Results

We open-source the ORACLE library of methods on deep learned collision-free navigation of aerial robots that assume a) no access to a map of the environment or an estimate of the robot’s position, and presents robust sim2real transfer. ORACLE enables safe uncertainty-aware flight, while its visually-attentive variant (A-ORACLE) combines that capacity with implicit information sampling, and seVAE-ORACLE alters the architecture to offer modularization and partial training on both synthetic and real data (if available).

Reinforcement Learning for Collision-free Flight Exploiting Deep Collision Encoding

This work contributes a novel deep navigation policy that enables collision-free flight of aerial robots based on a modular approach exploiting deep collision encoding and reinforcement learning. The proposed solution builds upon a deep collision encoder that is trained on both simulated and real depth images using supervised learning such that it compresses the high-dimensional depth data to a low-dimensional latent space encoding collision information while accounting for the robot size.

Semantically-enhanced Deep Collision Prediction for Autonomous Navigation using Aerial Robots

This work contributes a novel and modularized learning-based method for aerial robots navigating cluttered environments containing hard-to-perceive thin obstacles without assuming access to a map or the full pose estimation of the robot. The proposed solution builds upon a semantically-enhanced Variational Autoencoder that is trained with both real-world and simulated depth images to compress the input data, while preserving semantically-labeled thin obstacles and handling invalid pixels in the depth sensor's output.

Motion Primitives-based Navigation Planning using Deep Collision Prediction

This work contributes a method to design a novel navigation planner exploiting a learning-based collision prediction network. The neural network is tasked to predict the collision cost of each action sequence in a predefined motion primitives library in the robot's velocity-steering angle space, given only the current depth image and the estimated linear and angular velocities of the robot.