Mediaspace scheduled maintenance: Aug 25, 2026 07:00 - 12:00 AM. During this time, videos will be temporarily unavailable. Check status updates.

Lecture

Vision-based robotic perception

Description

This lecture by the instructor M. Chli focuses on the challenges and opportunities in vision-based robotic perception, covering topics such as high-fidelity SLAM, scene reconstruction for interaction and path-planning, place recognition using deep learning, event cameras for tracking, continuous-time SLAM, and collaborative SLAM. The lecture delves into cutting-edge techniques like real-time wide-baseline place recognition, event cameras for high-fidelity SLAM, and semantic-aware planning using reinforcement learning. It also explores the development of collaborative visual perception and intelligence for robotic autonomy.

Official source

Related concepts (32)

Robotics

Robotics is an interdisciplinary branch of electronics and communication, computer science and engineering. Robotics involves the design, construction, operation, and use of robots. The goal of robotics is to design machines that can help and assist humans. Robotics integrates fields of mechanical engineering, electrical engineering, information engineering, mechatronics engineering, electronics, biomedical engineering, computer engineering, control systems engineering, software engineering, mathematics, etc.

Deep reinforcement learning

Deep reinforcement learning (deep RL) is a subfield of machine learning that combines reinforcement learning (RL) and deep learning. RL considers the problem of a computational agent learning to make decisions by trial and error. Deep RL incorporates deep learning into the solution, allowing agents to make decisions from unstructured input data without manual engineering of the state space. Deep RL algorithms are able to take in very large inputs (e.g.

Reinforcement learning

Reinforcement learning (RL) is an area of machine learning concerned with how intelligent agents ought to take actions in an environment in order to maximize the notion of cumulative reward. Reinforcement learning is one of three basic machine learning paradigms, alongside supervised learning and unsupervised learning. Reinforcement learning differs from supervised learning in not needing labelled input/output pairs to be presented, and in not needing sub-optimal actions to be explicitly corrected.

Night vision

Night vision is the ability to see in low-light conditions, either naturally with scotopic vision or through a night-vision device. Night vision requires both sufficient spectral range and sufficient intensity range. Humans have poor night vision compared to many animals such as cats, foxes and rabbits, in part because the human eye lacks a tapetum lucidum, tissue behind the retina that reflects light back through the retina thus increasing the light available to the photoreceptors.

Night-vision device

A night-vision device (NVD), also known as a night optical/observation device (NOD), night-vision goggle (NVG), is an optoelectronic device that allows visualization of images in low levels of light, improving the user's night vision. The device enhances ambient visible light and converts near-infrared light into visible light which can be seen by the user; this is known as I2 (). By comparison, viewing of infrared thermal radiation is referred to as thermal imaging and operates in a different section of the infrared spectrum.

Related lectures (50)

Acquiring Data for Learning

Explores training robots through reinforcement learning and learning from demonstration, highlighting challenges in human-robot interaction and data collection.

Robot Learning and Control

Covers learning and adaptive control for robots, focusing on real-time reactivity and path planning using dynamical systems.

Scaffolding and Imitation Learning: Human Principles for Robots

Explores transferring human learning principles to robots, focusing on manipulation skill learning and task planning.

Perception: Data-Driven Approaches

Explores perception in deep learning for autonomous vehicles, covering image classification, optimization methods, and the role of representation in machine learning.

Collective Learning Dynamics: Similarity Exploitation