Saturday, March 23, 2024

Mojo5 - Moving forward in the design (#5)

In our latest chapter of the Mojo5 saga, we're diving deep into the tangible world of robot building, where every breakthrough is hard-won, and every detail counts. This update is all about the real, hands-on progress we've made since last time, focusing on practical challenges and our solutions.

Here's what we've been up to:

Refining the Yaw Axis: We've successfully printed and assembled the new components that accommodate Mojo5's improved yaw movement. This time around, we're talking about the nuts and bolts—literally. Using 30mm M3 screws, to provide the Axis for the Yaw. Now, it is important to consider the build order as the 30mm bolt is added through the servo mount to the yaw frame. The locking nuts and Yaw Gear have to be added before passing through the frame.

Mojo5 - New 3rd Axis added to design

In the photo you can see the original paper sketch, and the 3D printed version. The previous post has the openSCAD version.


Putting Strength to the Test: We didn't stop at design improvements. To really see what Mojo5 can handle, we added a 370g load to its leg. It's essential for us to keep testing the limits and capabilities of our design, especially when it comes to real-world functionality. You can catch this test in action on our YouTube channel https://youtube.com/shorts/EplPBtQ46vw , where we've captured the whole process.



Streamlining the Design: while always on iterating the next improvement, we've started to pare down Mojo5, removing unnecessary parts and integrating a smaller Abductor Servo. This step might seem like we're taking things away, but in reality, we're optimizing for efficiency and performance. Sometimes the best part is the part you leave out - Engineering saying.

Mojo5 - The next iteration, removing un-required structure


Looking Back and Charging Ahead

These updates are more than just progress; they're a testament to the iterative nature of building robots. Each step, whether it's a new screw or a test under load, teaches us something vital about our design and its possibilities.

And as we dive into refining Mojo5 further, removing the extraneous and focusing on what truly matters, we're reminded of the essence of hobby robotics: it's a journey of constant learning, adjusting, and, most importantly, enjoying the process.

We Want to Hear From You

Your thoughts, feedback, and ideas have been incredibly valuable throughout this project. As we continue to navigate the complexities and joys of robot building, we're eager to hear more from you. What challenges have you faced in your projects? How do you approach problem-solving and iteration?

Let's keep the conversation going. Stay tuned for more updates as we push forward, one prototype at a time.

Catch you in the next post!

Tuesday, March 12, 2024

Mojo5 - Rethinking for the Yaw (#4)

Hey everyone! Diving into the heart of our Mojo5 robot project, we’ve hit that exhilarating moment where stepping forward means transforming everything from the ground up. Realizing this early in the prototyping phase? Priceless.

In this fourth installment, we’re rolling out the 'Yaw' – and yes, for our savvy crew following along, that's our latest dive into giving our robot an extra degree of freedom. This isn't just any move; it's what will let our robot's foot pivot with finesse, moving in and out from under the hip, enhancing its agility.

Mojo5 "yaw" mount around servos mount

Our solution? Introducing a lateral axis by creatively engineering a yaw mount that wraps around our existing servo setup. For those of you who’ve been with us, you know the servos and mounts are already pushing our size limits. So, in a stroke of insight, we decided to rotate the entire servo mount by 90 degrees. It’s a straightforward yet revolutionary tweak that cuts through our design challenges, though it does mean we’ve got our work cut out for us updating the OpenSCAD code. But, considering we're still early in the design phase, it's the perfect time for such ambitious changes.

Working in the CAD system really shines here, allowing us to simulate and verify our modifications in real-time. We managed to dial in the yaw movement to achieve +30 and -30 degrees of motion by adjusting just one variable. It’s clear, though, we’re not done iterating; we’ll need to push beyond these angles for the mobility we’re aiming for.

Mojo5: Yaw at +30 degrees

Figure: Yaw at -30 degrees

These figures highlight not just the potential of our design but the iterative nature of robotics itself. While 'Yaw' may be our current terminology, it's the concept and the progress that truly matter.

As we navigate through these updates, your insights and enthusiasm fuel this journey. The path of rapid prototyping is fraught with revisions, but each step brings us closer to realizing the full capabilities of our Mojo5. Stay tuned for the next leap forward!


Note: the correct term for "yaw" would likely be abduction and adduction:

  • Abduction is the movement away from the central axis of the body or, in this case, moving the leg outward from the body's midline.
  • Adduction is the movement towards the body’s central axis or moving the leg inward toward the body's midline.

Sunday, March 3, 2024

Mojo5 - Testing the Leg Design (#3)

Mojo5 Leg Design Test Setup
Mojo5 - Leg Design Test setup

It has been a few months since had some focus on this robot. As a stalled project, it always sits in the back of your head. The next task was to test the configuration to see if this design would be strong enough to lift its own weight in addition to the additional weight of the robot - Chassis, controller, battery, etc.

This weekend, I had a clear desk and I set up the test stand - which failed immediately, snapping my quick clamp with a loud snap. After some time, it occurred to me that I could have the 'chopsticks' extend out in two directions and this would be sufficient to test. Voila!

The robot Leg design with its cam and push rods was easily able to lift 450g + in addition to its own weight. I could not easily strap any additional weight to it. But, I am quite satisfied with this amount of payload for the moment!

Hey - did you notice I am using a Champagne Cork for the foot! :)

Saturday, January 13, 2024

A more RUGGED robot platform for Exploration

continuing on the these of robotic design, with the help of AI (robotics) tools... 

 It seems our last attempts resulted in an unexpected robot! The broad pink and white stripes, soft lighting, and big goofy grin resulted in a "Total Adorable Robot".

Extra Adorable, Totally Not Evil Robot

However, I do not think that that Robot would survive very long in the Sonoran Desert!  There for, back to the discussion, and lets add some design that would work in a sandy, rocky region:


The first in the conversation, when reminded that the robot needed operate in rocky or sandy environments, it added broad wheels in an awkward arrangement.  I could imagine this also as a treaded solution. The bigger innovation perhaps is having the sensor platform as a (potentially) pivoting top component over the drive chassis. The streamlined frame looks like it would handle wind storms much better. The front sensors and display may need some protection and covering. overall, this is a much more robust robot.  But where is the manipulator arm?

The next variation of the prompt placed the robot in an icy, rocky environment and requested it have a manipulator that inspects geology:


The wheels of this Robot are considerably more realistic. It is also quite plausible that this robot would fall over. If you examine closely, there is a suggestion of the manipulator arm jutting out between wheels, but it gets blended into the axel and is lost. 

The next request required that the manipulator be the focus of the image.


This version has even more rugged wheels and a top structre that looks like it could support a wide variety of payload. The manipulator arm is placed in a difficult position, but looks robust and effective.

The Rugged, Wheeled Hexapod:

What if the Wheels of the robot were replaced with rugged manipulators with wheels? The robot could crawl over rocks. Here is a potential variant:


I like this concept robot a lot. It would require very strong actuators and some compliant joints. By having some wheel motion capability at the end of the manipulators, the robot could roll and climb in difficult terrain. The top structure has the appearance of a turret, to move to present its sensors in all directions.

There is a lot of potential with a robot design like this.

For those interested in learning how OpenAI's ChatGPT and DALLE-3 work, the last three images were all generated using the exact same prompt. Here you can see how variation is introduced when executing the same prompt.


and once again:



Prompt: 
A robust, medium-sized exploration robot designed for rugged terrains, now uniquely featuring six multipurpose manipulator arms, used for both agile movement and examination. The robot has no wheels and moves by crawling on these manipulator arms. The body of the robot is adorned with broad pink and white stripes, presenting a friendly appearance. It has smooth, rounded contours, similar to an animal-like form. A digital display on the front shows a goofy grin, adding to its welcoming demeanor. The manipulator arms are made of strong, lightweight material, matching the robot's color scheme. These arms are intricately designed, demonstrating their flexibility and dexterity as the robot crawls across a challenging landscape, using them to navigate as well as examine geological features. Soft, warm lighting and clear branding with labels like 'Research Robot' and 'TOTALLY Not Evil!' are included in the design, with a focus on the unique functionality and design of the manipulator arms in the rugged environment.

Interesting what might actual make these images unique.  Once rendered it would be almost impossible to re-render the exact same picture.  See for yourself how very different they are drawn, given the same instructions.

Of course, they are all supposed to have six arms, and the last two only have four! They are also each supposed to have "Research Robot" and "Totally Not Evil!" stickers on them. It seems we stil have some more learning and progress to get DALLE3 on task, even when it was in a moderated thread with ChatGPT.



Friday, January 12, 2024

A Robotic Platform for Remote Exploration

A Robotic Platform for Remote Exploration, Sensing, and Monitoring


Earth Exploring robot concept that is "Totally" Not Evil!

Me and another Robot (LLM), design a robot for earth exploring!

let's design a robot platform for remote exploration, sensing, and monitoring.  What components would it need?

Designing a robot for remote exploration, sensing, and monitoring involves a combination of hardware and software components, each tailored to the specific requirements of the environment it will operate in and the tasks it will perform. Here's a detailed breakdown:


Hardware Components

1. Mobility System: 

   - Type: Depends on the terrain. Wheeled or tracked systems for ground, propellers for aerial, or thrusters for underwater exploration.

   - Material: Durable and lightweight, like carbon fiber or reinforced plastics.

[x] let us consider going for a rocky, sandy terrain with some vegetation, should be able to climb up a moderate slope.

2. Power Source:

   - Options: Solar panels, rechargeable batteries, or fuel cells.

   - Consideration: Longevity and environmental impact.

[x] electric and rechargeable, certainly. perhaps with multiple ports, incase someone wants to share a few watts of power.

3. Sensors:

   - Environmental Sensors: Temperature, humidity, atmospheric pressure.

   - Navigation Sensors: GPS, IMU (Inertial Measurement Units), lidar, sonar.

   - Specialized Sensors: Chemical sensors, radiation detectors, biological sensors.

[x] leave lots of room for sensors, that is what this is all about.

4. Communication System:

   - Options: Satellite communication for remote areas, Wi-Fi or Bluetooth for urban environments.

   - Redundancy: Essential to ensure constant communication.

[x] multiple options, use them all. perhaps even piggybacking on someone's iphone like an airtag?

5. Data Storage and Processing Unit:

   - Type: Onboard computer with robust processing capabilities.

   - Requirement: Must handle large amounts of data from sensors.

[x] bigger the better. just put it in a safe environment.

6. Robotic Arm or Manipulator: (why not?)

   - Capabilities: Picking, sampling, or minor manipulation tasks.

   - Design: Lightweight and flexible.

[x] absolute!  what is a robot without a manipulator or two, three...

7. Protective Casing:

   - Purpose: Protect against environmental conditions like temperature extremes, water, dust, etc.

   - Material: Dependent on the environment (e.g., waterproof materials for underwater robots).

[x] this will be extreme use them all.

8. Camera System:

   - Types: High-resolution visual, infrared for night vision, possibly 3D cameras.

[x] need cameras, many! we are all watchers for where this robot can go.

9. Emergency Systems:

   - Components: Emergency shut-off, self-diagnostic capabilities, fault-tolerant design.

[x] this robot is on its own, it will need to be self-reliant. not sure on the shut-off though?


Software Components

1. Operating System:

   - Type: Real-time operating system for immediate response to sensor inputs.

[x] both OS and controller, ROS2 is a good start, with subcomponents and watchdogs on controller circuits.

2. Navigation and Mapping Software:

   - Function: Path planning, obstacle avoidance, and real-time map generation.

[x] SLAM! Bam, thankyou mam!

3. Data Analysis Software:

   - Purpose: Process sensor data to extract meaningful information.

[x] let us do some on site, and send the rest to the mothership.

4. Communication Protocol:

   - Design: Secure and reliable, able to handle varying signal strengths.

[x] assume sparse and periodic communications, this is reality really.

5. AI and Machine Learning Algorithms:

   - Application: Autonomous decision making, pattern recognition, predictive maintenance.

[x] the fun part!

6. User Interface:

   - Features: Remote control capabilities, data visualization tools, alerts and notifications system.

[x] all of the above. lets give it some on-board UI, as well as the remote operations.


Additional Considerations

- Modularity: Designing the robot with interchangeable parts can enhance versatility and ease of maintenance.

[x] done!

- Scalability: The design should allow for easy updates and integration of new technologies.

[x] absolute

- Sustainability: Consider the environmental impact of the robot during its lifecycle.

[x] be kind to earth.

- Legal and Ethical Compliance: Ensure compliance with regulations in areas of operation, especially for data handling and privacy.

[x] don't hurt Hooomans!  after all it must be TOTALLY Not Evil!

- Safety Features: Crucial if the robot operates in public spaces or near humans.

[x] hey, don't hurt the meatbags!


Speculative Technologies

- Swarm Intelligence: For tasks that require large-scale monitoring, using a group of smaller robots working in a coordinated fashion.

[x] oh yeah! Robots that have robots!

- Advanced AI: For autonomous decision-making in unpredictable environments.

[o] so easy to say, what does this even mean anymore?

- Wireless Power Transfer: To recharge without physical connectors, enhancing the robot's autonomy.

[x] or better yet, lets harvest it from 'sources'


I think it would need to look friendly so that it is not abused by Hooomans that find it. 

Absolutely, the robot's appearance plays a crucial role in how it's perceived and treated by the public, especially if it's operating in areas where it might encounter people. A friendly, non-threatening design can help to mitigate the risk of abuse or vandalism. Here are some design aspects to consider for a friendly appearance:

Design Elements for a Friendly Appearance

1. Color Scheme:

   - Selection: Choose soft, approachable colors. Pastels or bright, non-intimidating colors like light blue, green, or yellow can convey friendliness.

   - Purpose: Avoid aggressive or military-like colors that might be perceived as threatening.

[x] lets go with broad Pink and White stripes.

2. Shape and Form:

   - Design: Rounded edges and smooth contours are generally seen as more friendly and less aggressive than sharp angles and points.

   - Inspiration: Take cues from popular consumer electronics or characters in family-friendly media that are known for their approachable designs.

[x] Animals have rounded edges too.

3. Size and Scale:

   - Proportion: Not too large to be intimidating, but not so small as to be easily tampered with. A medium-sized build can be optimal.

   - Aspect: Humanoid or animal-like features can be engaging and relatable.

[x] medium is good.

4. Facial Features or Equivalent:

   - Display: If applicable, incorporate a simple, digital face or emotive lights. Expressions like a smile or blinking lights can create a sense of friendliness and approachability.

   - Interaction: Features that react to human presence (like turning towards someone when they speak) can foster a sense of interaction.

[x] true! maybe with a goofy grin on it.

5. Sound and Voice:

   - Tone: A friendly, non-threatening voice for any audio communication.

   - Sound Effects: Gentle, pleasant beeps or musical tones instead of harsh or alarming sounds.

[x] beep bop! Hello!   -- thanks R2D2!

6. Branding and Signage:

   - Labels: Clear, friendly branding with logos or mascots that suggest helpfulness and positivity.

   - Information: Displaying its purpose (“Research Robot”, “Environmental Monitoring”, etc.) can help people understand its presence and mission.

[x] should clearly state that it is "TOTALLY Not Evil!"