An Embarrassingly Pragmatic Introduction to Vision-based Autonomous Robots

• URL: http://arxiv.org/abs/2112.05534v2
• Date: Tue, 14 Dec 2021 05:19:00 GMT
• Title: An Embarrassingly Pragmatic Introduction to Vision-based Autonomous Robots
• Authors: Marcos V. Conde
• Abstract summary: We develop a small-scale autonomous vehicle capable of understanding the scene using only visual information. We discuss the current state of Robotics and autonomous driving and the technological and ethical limitations that we can find in this field.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Autonomous robots are currently one of the most popular Artificial Intelligence problems, having experienced significant advances in the last decade, from Self-driving cars and humanoids to delivery robots and drones. Part of the problem is to get a robot to emulate the perception of human beings, our sense of sight, replacing the eyes with cameras and the brain with mathematical models such as Neural Networks. Developing an AI able to drive a car without human intervention and a small robot to deliver packages in the city may seem like different problems, nevertheless from the point of view of perception and vision, both problems have several similarities. The main solutions we currently find focus on the environment perception through visual information using Computer Vision techniques, Machine Learning, and various algorithms to make the robot understand the environment or scene, move, adapt its trajectory and perform its tasks (maintenance, exploration, etc.) without the need for human intervention. In this work, we develop a small-scale autonomous vehicle from scratch, capable of understanding the scene using only visual information, navigating through industrial environments, detecting people and obstacles, or performing simple maintenance tasks. We review the state-of-the-art of fundamental problems and demonstrate that many methods employed at small-scale are similar to the ones employed in real Self-driving cars from companies like Tesla or Lyft. Finally, we discuss the current state of Robotics and autonomous driving and the technological and ethical limitations that we can find in this field.

Related papers

• Commonsense Reasoning for Legged Robot Adaptation with Vision-Language Models [81.55156507635286]
  Legged robots are physically capable of navigating a diverse variety of environments and overcoming a wide range of obstructions. Current learning methods often struggle with generalization to the long tail of unexpected situations without heavy human supervision. We propose a system, VLM-Predictive Control (VLM-PC), combining two key components that we find to be crucial for eliciting on-the-fly, adaptive behavior selection.
  arXiv  Detail & Related papers  (2024-07-02T21:00:30Z)
• HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulation [50.616995671367704]
  We present a high-dimensional, simulated robot learning benchmark, HumanoidBench, featuring a humanoid robot equipped with dexterous hands. Our findings reveal that state-of-the-art reinforcement learning algorithms struggle with most tasks, whereas a hierarchical learning approach achieves superior performance when supported by robust low-level policies.
  arXiv  Detail & Related papers  (2024-03-15T17:45:44Z)
• Giving Robots a Hand: Learning Generalizable Manipulation with Eye-in-Hand Human Video Demonstrations [66.47064743686953]
  Eye-in-hand cameras have shown promise in enabling greater sample efficiency and generalization in vision-based robotic manipulation. Videos of humans performing tasks, on the other hand, are much cheaper to collect since they eliminate the need for expertise in robotic teleoperation. In this work, we augment narrow robotic imitation datasets with broad unlabeled human video demonstrations to greatly enhance the generalization of eye-in-hand visuomotor policies.
  arXiv  Detail & Related papers  (2023-07-12T07:04:53Z)
• Affordances from Human Videos as a Versatile Representation for Robotics [31.248842798600606]
  We train a visual affordance model that estimates where and how in the scene a human is likely to interact. The structure of these behavioral affordances directly enables the robot to perform many complex tasks. We show the efficacy of our approach, which we call VRB, across 4 real world environments, over 10 different tasks, and 2 robotic platforms operating in the wild.
  arXiv  Detail & Related papers  (2023-04-17T17:59:34Z)
• HERD: Continuous Human-to-Robot Evolution for Learning from Human Demonstration [57.045140028275036]
  We show that manipulation skills can be transferred from a human to a robot through the use of micro-evolutionary reinforcement learning. We propose an algorithm for multi-dimensional evolution path searching that allows joint optimization of both the robot evolution path and the policy.
  arXiv  Detail & Related papers  (2022-12-08T15:56:13Z)
• See, Hear, and Feel: Smart Sensory Fusion for Robotic Manipulation [49.925499720323806]
  We study how visual, auditory, and tactile perception can jointly help robots to solve complex manipulation tasks. We build a robot system that can see with a camera, hear with a contact microphone, and feel with a vision-based tactile sensor.
  arXiv  Detail & Related papers  (2022-12-07T18:55:53Z)
• Surround-View Cameras based Holistic Visual Perception for Automated Driving [0.6091702876917281]
  We focus on developing near-field perception algorithms with high performance and low computational complexity. These capabilities for computers is critical for various applications, including self-driving cars, augmented reality, and architectural surveying.
  arXiv  Detail & Related papers  (2022-06-11T14:51:30Z)
• Neuroscience-inspired perception-action in robotics: applying active inference for state estimation, control and self-perception [2.1067139116005595]
  We discuss how neuroscience findings open up opportunities to improve current estimation and control algorithms in robotics. This paper summarizes some experiments and lessons learned from developing such a computational model on real embodied platforms.
  arXiv  Detail & Related papers  (2021-05-10T10:59:38Z)
• Design and Development of Autonomous Delivery Robot [0.16863755729554888]
  We present an autonomous mobile robot platform that delivers the package within the VNIT campus without any human intercommunication. The entire pipeline of an autonomous robot working in outdoor environments is explained in this thesis.
  arXiv  Detail & Related papers  (2021-03-16T17:57:44Z)
• Sensorimotor representation learning for an "active self" in robots: A model survey [10.649413494649293]
  In humans, these capabilities are thought to be related to our ability to perceive our body in space. This paper reviews the developmental processes of underlying mechanisms of these abilities. We propose a theoretical computational framework, which aims to allow the emergence of the sense of self in artificial agents.
  arXiv  Detail & Related papers  (2020-11-25T16:31:01Z)
• Morphology-Agnostic Visual Robotic Control [76.44045983428701]
  MAVRIC is an approach that works with minimal prior knowledge of the robot's morphology. We demonstrate our method on visually-guided 3D point reaching, trajectory following, and robot-to-robot imitation.
  arXiv  Detail & Related papers  (2019-12-31T15:45:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.