Teaching Continuity in Robotics Labs in the Age of Covid and Beyond
- URL: http://arxiv.org/abs/2105.08839v1
- Date: Tue, 18 May 2021 21:38:26 GMT
- Title: Teaching Continuity in Robotics Labs in the Age of Covid and Beyond
- Authors: R. Pito Salas
- Abstract summary: This paper argues that training of future Roboticists and Robotics Engineers in Computer Science departments, requires the extensive direct work with real robots.
This is exactly the problem that Robotics Labs encountered in early 2020, at the start of the Covid pandemic.
The exciting insight in the conclusion is that the work that was encouraged and triggered by a pandemic seems to have very positive longer-term benefits.
- Score: 0.0
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: This paper argues that training of future Roboticists and Robotics Engineers
in Computer Science departments, requires the extensive direct work with real
robots, and that this educational mission will be negatively impacted when
access to robotics learning laboratories is curtailed. This is exactly the
problem that Robotics Labs encountered in early 2020, at the start of the Covid
pandemic. The paper then turns to the description of a remote/virtual robotics
teaching laboratory and examines in detail what that would mean, what the
benefits would be, and how it may be used. Part of this vision was implemented
at our institution during 2020 and has been in constant use since then. The
specific architecture and implementation, as far as it has been built, is
described. The exciting insight in the conclusion is that the work that was
encouraged and triggered by a pandemic seems to have very positive longer-term
benefits of increasing access to robotics education, increasing the ability of
any one institution to scale their robotics education greatly, and potentially
do this while reducing costs.
Related papers
- Octo: An Open-Source Generalist Robot Policy [88.14295917143188]
We introduce Octo, a large transformer-based policy trained on 800k trajectories from the Open X-Embodiment dataset.
It can be effectively finetuned to robot setups with new sensory inputs and action spaces within a few hours on standard consumer GPU.
We also perform detailed ablations of design decisions for the Octo model, from architecture to training data, to guide future research on building generalist robot models.
arXiv Detail & Related papers (2024-05-20T17:57:01Z) - Contextual Affordances for Safe Exploration in Robotic Scenarios [1.7647943747248804]
This paper explores the use of contextual affordances to enable safe exploration and learning in robotic scenarios targeted at the home.
We propose a simple state representation that allows us to extend contextual affordances to larger state spaces.
In the long term, this work could be the foundation for future explorations of human-robot interactions in complex domestic environments.
arXiv Detail & Related papers (2024-05-10T12:12:38Z) - 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) - Self-Improving Robots: End-to-End Autonomous Visuomotor Reinforcement
Learning [54.636562516974884]
In imitation and reinforcement learning, the cost of human supervision limits the amount of data that robots can be trained on.
In this work, we propose MEDAL++, a novel design for self-improving robotic systems.
The robot autonomously practices the task by learning to both do and undo the task, simultaneously inferring the reward function from the demonstrations.
arXiv Detail & Related papers (2023-03-02T18:51:38Z) - Towards Long-term Autonomy: A Perspective from Robot Learning [13.38855419752331]
Service robots are expected to be able to operate autonomously for long periods of time without human intervention.
In this paper, we examine the problem of long-term autonomy from the perspective of robot learning, especially in an online way.
arXiv Detail & Related papers (2022-12-24T18:32:14Z) - GenLoco: Generalized Locomotion Controllers for Quadrupedal Robots [87.32145104894754]
We introduce a framework for training generalized locomotion (GenLoco) controllers for quadrupedal robots.
Our framework synthesizes general-purpose locomotion controllers that can be deployed on a large variety of quadrupedal robots.
We show that our models acquire more general control strategies that can be directly transferred to novel simulated and real-world robots.
arXiv Detail & Related papers (2022-09-12T15:14:32Z) - HeRo 2.0: A Low-Cost Robot for Swarm Robotics Research [2.133433192530999]
This paper presents the design of a novel platform for swarm robotics applications that is low cost, easy to assemble using off-the-shelf components, and deeply integrated with the most used robotic framework: ROS (Robot Operating System)
The robotic platform is entirely open, composed of a 3D printed body and open-source software.
Results demonstrate that the proposed mobile robot is very effective given its small size and reduced cost, being suitable for swarm robotics research and education.
arXiv Detail & Related papers (2022-02-24T22:23:14Z) - REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy
Transfer [57.045140028275036]
We consider the problem of transferring a policy across two different robots with significantly different parameters such as kinematics and morphology.
Existing approaches that train a new policy by matching the action or state transition distribution, including imitation learning methods, fail due to optimal action and/or state distribution being mismatched in different robots.
We propose a novel method named $REvolveR$ of using continuous evolutionary models for robotic policy transfer implemented in a physics simulator.
arXiv Detail & Related papers (2022-02-10T18:50:25Z) - Dual-Arm Adversarial Robot Learning [0.6091702876917281]
We propose dual-arm settings as platforms for robot learning.
We will discuss the potential benefits of this setup as well as the challenges and research directions that can be pursued.
arXiv Detail & Related papers (2021-10-15T12:51:57Z) - Know Thyself: Transferable Visuomotor Control Through Robot-Awareness [22.405839096833937]
Training visuomotor robot controllers from scratch on a new robot typically requires generating large amounts of robot-specific data.
We propose a "robot-aware" solution paradigm that exploits readily available robot "self-knowledge"
Our experiments on tabletop manipulation tasks in simulation and on real robots demonstrate that these plug-in improvements dramatically boost the transferability of visuomotor controllers.
arXiv Detail & Related papers (2021-07-19T17:56:04Z) - Projection Mapping Implementation: Enabling Direct Externalization of
Perception Results and Action Intent to Improve Robot Explainability [62.03014078810652]
Existing research on non-verbal cues, e.g., eye gaze or arm movement, may not accurately present a robot's internal states.
Projecting the states directly onto a robot's operating environment has the advantages of being direct, accurate, and more salient.
arXiv Detail & Related papers (2020-10-05T18:16:20Z)
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.