3D Scene Compression for Autonomous Driving using Neural Radiance Fields

Neural Radiance Fields (NeRFs) have showcased remarkable effectiveness in capturing complex 3D scenes and synthesizing novel viewpoints. By inherently capturing the entire scene in a compact representation, they offer a promising avenue for applications such as simulators, where efficient storage of real-world data, fast rendering and dynamic...

Grasp recognition with spatiotemporal deep learning and proximity sensors in transradial prostheses

The traumatic loss of a hand is a horrific experience usually followed by significant psychological, functional and rehabilitation challenges. Even though much progress has been made in the past decades, the prosthetic challenge of restoring the human hand functionality is still far from being achieved. Autonomous prosthetic hands showed...

Multi-class Trajectory Prediction in Urban Traffic using the View-of-Delft Dataset

Critical to the safe application of autonomous vehicles is the ability to accurately predict the future motion of agents surrounding the vehicle. This is especially important - and challenging - in urban traffic, where vehicles share the road with Vulnerable Road Users (VRUs) such as pedestrians and cyclists. However, the majority of the...

Deep learning based motion prediction algorithms for autonomous driving

In order to ensure that autonomous driving vehicles can make appropriate driving decisions based on the surrounding situation, motion prediction algorithms are used to generate the driving decision output, which will then be used for guiding the trajectory of the vehicle. In general, the output of the motion prediction algorithm is a series that...

Structural Distillation for Object Detection

Knowledge Distillation (KD) is a well-known training paradigm in deep neural networks where knowledge acquired by a large teacher model is transferred to a small student. KD has proven to be an effective technique to significantly improve the student's performance for various tasks including object detection. As such, KD techniques mostly rely...

Autonomous Navigation around Asteroids using Convolutional Neural Networks

Missions to small bodies are increasingly gaining interest as they might hold the secrets to our solar system’s origin while some are also posing a threat to life on Earth. The small size and irregular shape result in complex dynamics complicating the close-proximity operations. Furthermore, due to the long round-trip time communication delays...

Pedestrian Detection and Tracking for Mobile Robots in Human Environments

With the performance of current motion planning methods being highly dependent on the quality of the perception system, robust 3D multi-object detection and tracking are vital for autonomous driving applications. Despite all the advancements in 2D and 3D object detectors, robust tracking of pedestrians in dense scenarios is still a challenging...

Reinforcement Learning approach for decision-making in driver control shifting for semi-autonomous driving

Semi-autonomous driving innovations aim to bridge the gap to fully autonomous driving by co-operating with human drivers to lead to optimal choices on who should drive in different scenarios by offering different automation levels. However, in the present day, known semi-autonomous driving solutions do not generalise to every complex case of...

Safe and natural navigation in dynamic environments, learned from human behavior

Social Navigation is the task of robot motion planning in an environment shared with humans.This is an especially hard sub-problem of motion planning because the planner has to dealwith a dynamic, continuous and unpredictable environment. We present a local motionplanner, namely Neural Network Model Predictive Control, for autonomous ground...

The Landing of a Quadcopter on Inclined Surfaces using Reinforcement Learning

Deep Reinforcement Learning (DRL) enables us to design controllers for complex tasks with a deep learning approach. It allows us to design controllers that are otherwise cumbersome to design with conventional control methodologies. Often, an objective for RL is binary in nature. However, exploring in environments with sparse rewards is a problem...