micahcorah - Network

For more detail on me and my work, you can also check out my website: https://www.micahcorah.com/

For more detail on me and my work, you can also check out my website: https://www.micahcorah.com/

You may focus on research involving theory (planning and control) and simulation, experiments with aerial robots in motion capture (esp....

You may focus on research involving theory (planning and control) and simulation, experiments with aerial robots in motion capture (esp. teams of robots filming people!), and eventually field experiments (Mines has a mine! https://mining.mines.edu/edgar-experimental-mine/ ⚒️🪨).

Also, if you want to join my lab:What would you do, and what kind of background might you have?I expect to primarily hire students with...

Also, if you want to join my lab:

What would you do, and what kind of background might you have?

I expect to primarily hire students with backgrounds in computer science or engineering. And, we will do work spanning from theory to practice for aerial and mobile robots.

At Mines, I plan research aerial robots, view planning, and multi-robot teams with applications to #drone filming and videography,...

At Mines, I plan research aerial robots, view planning, and multi-robot teams with applications to #drone filming and videography, infrastructure inspection, and mine safety, search and rescue.

If any of this piques your interest, and you are considering applying to graduate programs (MS or PhD) this fall, please reach out!

I am also excited because 🏔️Colorado is a wonderful place to live (and where I grew up). Golden is nestled at the base of the rockies...

I am also excited because 🏔️Colorado is a wonderful place to live (and where I grew up). Golden is nestled at the base of the rockies and provides outstanding access for outdoor activities ⛷️🥾🚵‍♀️as well as close proximity to Denver 🌆

I love the people here, and I am super excited to be a part of this growing department and also for the new #robotics graduate and...

I love the people here, and I am super excited to be a part of this growing department and also for the new #robotics graduate and undergraduate programs.
https://robotics.mines.edu/

I am delighted to say that I will be joining the Colorado School of Mines CS@Mines 💻🤖 as an Assistant Professor 👨‍🏫 this...

I am delighted to say that I will be joining the Colorado School of Mines CS@Mines 💻🤖 as an Assistant Professor 👨‍🏫 this January!
#academia #academicchatter #academicmastodon

I am deeply disappointed to hear that the Chevy Bolt is being discontinued in favor of production of more electric trucks.This is a poor...

I am deeply disappointed to hear that the Chevy Bolt is being discontinued in favor of production of more electric trucks.

This is a poor choice both in terms of environmental impact and affordability of electric vehicles.
#electricvehicles

And, this is the gist of what I have been working on for the last year or so 😄🤖🛩️

And, this is the gist of what I have been working on for the last year or so 😄🤖🛩️

The result, is you end up with system dynamics that are quite different from other domains. In videography applications, robots without...

The result, is you end up with system dynamics that are quite different from other domains. In videography applications, robots without coordination will tend to collapse to common equilibria (e.g. to film the front of the most important person).

Then, explicit coordination via methods like greedy submodular optimization ends up being critical to task performance (e.g. maintaining a diversity of viewpoints that evenly cover a group of people).

This is where problems like multi-robot videography come in. In these settings, you want to optimize immediate views, and your rewards for...

This is where problems like multi-robot videography come in. In these settings, you want to optimize immediate views, and your rewards for observations at one moment might be independent of observations at any other time.

The reasons for why this happens are a little fuzzy. However, in my understanding this often comes down to implicit coordination....

The reasons for why this happens are a little fuzzy. However, in my understanding this often comes down to implicit coordination. Applications and systems that involve generating or maintaining a shared model (e.g. when tracking targets or mapping a building) often exhibit implicit coordination due to sharing models or sensor data. Knowing what other robots have previously observed is often sufficient for making decisions when good performance can be achieved just by observing something else.

However, there is another part to this story. While the methods I work with are powerful and often easy to implement, they are often studied...

However, there is another part to this story. While the methods I work with are powerful and often easy to implement, they are often studied primarily from a theoretic perspective. And, while these methods have been implemented on multi-robot systems, to the best of my knowledge, these implementations have not often demonstrated significant impacts on task performance.

This even works well in pretty general cases such as optimizing receding horizon trajectories (e.g. dynamic motions) with path costs,...

This even works well in pretty general cases such as optimizing receding horizon trajectories (e.g. dynamic motions) with path costs, terminal costs/constraints, and (some) non-collision constraints. Likewise, camera and sensor models can incorporate noise or raytracing against a complex environment without upsetting underlying assumptions.

Many perception objectives are submodular. For example, if you want to maximize coverage over the surface of a group of moving actors, you...

Many perception objectives are submodular. For example, if you want to maximize coverage over the surface of a group of moving actors, you will get a submodular objective.

From there, you can develop efficient and distributed algorithms to coordinate the team to maximize the quality of views.

Who here is interested in talking about #submodular optimization? 🤖My research is in #robotics, and I am applying these methods to...

Who here is interested in talking about #submodular optimization? 🤖

My research is in #robotics, and I am applying these methods to coordinate teams of aerial #robots to film moving actors such as animal groups or as in team sports!

Thread 👇

I don't see a whole lot of aerial robots, mobile robots, or even autonomous cars on here. There anyone I should be following?

I don't see a whole lot of aerial robots, mobile robots, or even autonomous cars on here. There anyone I should be following?

Anyone have tips on new tools and apps for using Mastodon?

Anyone have tips on new tools and apps for using Mastodon?

It is important to be aware of the human cost of training learning systems like ChatGPT (and for content moderation in general):...

It is important to be aware of the human cost of training learning systems like ChatGPT (and for content moderation in general): https://time.com/6247678/openai-chatgpt-kenya-workers/

Also, having my partner's support through this time goes a long way and on multiple levels.

Also, having my partner's support through this time goes a long way and on multiple levels.