9

Models. If you want to get good at control engineering, get good at modeling. If you want to impress a controls professor, get good at modeling. Models are how you're going to do 90 percent of your job, regardless of the controller style you choose to implement, so get good at modeling! If you want to try building a PID controller, first build a model of ...


6

better you say ? That's a nice wheeled robot you have there. Can I borrow it for a day? Thanks. Wow, it's really fast, I cannot keep up with it walking or running on the street. Truly an amazing machine. I'd like to show it to my friends and family. They are waiting in my flat that's on the 3rd floor up the stairs...what do you mean it cannot move over ...


5

It is usually a combination of 2 different pieces software. Generally a higher level software which implements most of your autonomy, advanced navigation algorithms, and a lower level software which deals with interfacing the motors, a simple state estimator, and accepts waypoint commands. Most common is ROS for the higher level software, and a PX4 for lower ...


4

ROS will work fine for this task. It will add some additional overhead for your Raspberry Pi but it is fairly small provided you only install the Robotic or Base configuration instead of the Full configuration and are using a headless (no GUI) Raspberry Pi install. My company uses ROS on self-driving cars and ROS has, so far, never been the cause of a fault -...


4

Have you considered forward-looking active sonar ? Perhaps using off-the-shelf fishfinder hardware? My understanding is that active sonar sensitive enough to detect (relatively soft) fish a hundred feet away can detect icebergs, large boats, rocks, shoreline, etc. over a mile away, because they are harder and so more reflective to the sonar. (My ...


3

You've asked more than one question, so I'll try to answer them in order. The Robotics community has not yet hit the limits of current hardware, so very little work is being done on the exotic cutting edge like neuromorphic hardware. The exception to this is software neural nets, which have come in and out of fashion for decades, and the Nv artificial ...


3

Regarding methodologies and tools, I recommend Chris Eliasmith's How to Build a Brain. It presents the Semantic Pointer Architecture (SPA), a cognitive model that has been realized in the open source Nengo toolkit. I have read the book's introduction and some of Eliasmith's papers, and so far the approach looks very promising.


3

There are standard protocols, and then there are proprietary protocols. The choice of what protocol to use depends on many things. Without listing the precise set of flight controllers you are planning to buy, it's difficult to provide anything more than a very general answer to this question.


3

This sounds a bit like a shopping question, but I'll provide what I know. The IEEE societies have always provided me a wealth of information. In addition to the Robotics Society, with its magazine and journal (IEEE Transactions on Robotics and Automation), they also host a fantastic annual conference. But there are other societies with robotics-related ...


3

I cannot comment on 'most common', but I can definitely share several tools and research efforts towards using FPGA for deep-learning. See my survey paper on FPGA-based accelerators for CNN which reviews 75+ recent papers. Some of these research projects have released their code, such as DNNWeaver. Also, see tools from companies such as Xilinx. Finally, see ...


3

m is an abstract representation of the map. In practice, m typically is some form of parametric model, whose parameters need to be estimated. Some very typical models: A set of point locations of objects in space. m becomes a vector of (x,y,[z]) coordinates (each for one object). A grid of cells which can have distinct states, in the simplest form just ...


2

For an autonomous boat, you might want to look into MOOS-IVP: http://oceanai.mit.edu/moos-ivp/pmwiki/pmwiki.php?n=Main.HomePageFull. It is similar to ROS in many respects, but geared towards autonomous boats instead of land vehicles. However, both middlewares are sufficiently abstract that they can handle land or sea vehicles just fine. However I can't ...


2

What you want is a real-time system. Generally, you can do this either in a standalone or a hosted environment. Standalone, otherwise known as bare-metal, means you write your code for a specific hardware, e.g. a microcontroller. That way, you have complete control of what executes and at what intervals, so you can be very precise. You can hardly go wrong ...


2

Nathan Ratliff has documented some very nice papers in Control Theory and Motion Optimization. You can access them here and here, resp. Particularly related to decision making problems, you might want to check Geoff Hollinger and Gaurav Sukhatme's course. The have a good list of readings in a logical flow. In general robotics, you may want to look at ...


2

I would like to mention that Fuzzy logic is still an active control system used in many industry applications. In garbage fired power plants, concrete aggregate firing, hydraulics, and the control of flow of powdered 'fluids' in foundries to name a few. However, I will admit, I've only seen them used in 'one off' difficult to model projects, such as power ...


2

Short answer: Fuzzy logic (FL) isn't applicable for robotics research, The long answer is, that in the 1980s as part of the fifth computer generation fuzzy logic was researched in Japan with the attempt to build intelligent advanced parallel computers, but the Japanese researchers have failed. Fuzzy logic isn't a technical idea but a philosophical ...


2

Fuzzy logic is definitely used in many of the control systems including but not limited to robotics. See this paper for an example: https://pdfs.semanticscholar.org/b9a7/332b03d46b3ee08b9d113e64714e6b668601.pdf and this: https://ieeexplore.ieee.org/document/1678143 If we consider fuzzy logic as dubious then we should do the same to probabilities. Both ...


2

What all control problems have in common is, that they can be solved with expert knowledge. A quadrotor needs a human expert for flight-dynamics while a pick&place robot needs somebody who is familiar with grasping objects. If it's possible to transfer domain knowledge into software the control problem is solved. The best way in doing so are domain ...


1

You should probably check out the universities below. I have read about some great research work done in the field of Aerial Robotics in these universities. They might not have a separate program as such for Aerial Robotics but there's extensive amount of projects that several students and researchers take part in under this area, be it through the ...


1

In order to generate the high levels of torque you are referring to, the actuator will certainly require a transmission of some sort. Above 500 Nm, cycloidal rather than harmonic drives are employed, usually preceded by a planetary input stage. Nabtesco, in Japan, is probably the current industry leader in these type of drives, which it brands as "RV" ...


1

I have not seen any industry-grade application of fuzzy logic in space, flight, automotive control systems. Fuzzy logic came during mid-60s and it gradually faded away due to several reasons: It did not solve any control problem that cannot already be solved by the existing methods at that time. Bad news, no major advantage in terms of extending the ...


1

Robotics software can be separated into environments and the motion controller itself. Notable example for robotics environments are ROS or Lejos. They are providing hardware capabilities to control the robot on a physical level and they have built in message passing features. On top of ROS and similar software so called robotics controllers are realized. ...


1

I am not aware of any online repository that particularly collects seminal papers in robotics. But I think anyone working or having worked in robotics for some time would more or less have their own collection of the so-called seminal papers in their field. So, here are motion planning-related papers that I think are within the scope of this question. (...


1

What you are looking to produce is certainly achievable using the ROS middleware. As Joshua has already pointed out, there will be some additional overhead but this should be relatively small. It is probably worth carrying out a literature search to investigate how other Autonomous Surface Vehicles (ASVs) have incorporated ROS into their software ...


1

Linear regulators are frequently used to control nonlinear systems. So are nonlinear controllers. Much depends on the system identification from a controls, not kinematics, perspective. I believe you are confusing the kinematics of motion with the system dynamics. Kinematics is the science of motion without regard to the forces and torques that ...


1

A friend of mine is senior developer at Infineon technologies for automotive applications. He told me that the best Inertial-MEMS for the automotive applications (which is basically your price target) are provided by BOSCH. After a quick search, I found the SMI130 which has pretty good signal-to-noise ratios. In addition this chip is available for 13$.


1

While Gazebo - and most other simulators - will allow you to simulate sensors, you have to realize that this the "weak" part of realtime simulators. Making an accurate simulated camera is really difficult. The result would therefore be great to test your integration and basic control algorithm behaviour (for instance that you move right when you should), but ...


1

Seems like this is a step towards what religious AI people would call a Singualarity. The goal to create a system which would function like the brain. I'am not into this field but I am into Robotics and AI. I can tell you that it's a step towards that dream. No one can say if its possible to do that because of Neuroscience finding weird things about the ...


1

Yes this is a broad question, you answered it partially is depends on your project. If you are working on a team, you probably would be responsible for the electrical, or mechanical, or navigation, and goes on, so you can go more deep inside the topic. But, anyway, you should know sufficient about the other team topics to integrate things together. If you ...


1

Generally, visual servoing is a way to measure your position relative to features that are seen on the camera, without having to know your absolute position. In other words, registering those features with those in a global frame would be a separate process. Remember that visual servoing is not limited to simply providing more data about your static ...


Only top voted, non community-wiki answers of a minimum length are eligible