Robots, AI, AVs: Its All Probability

May 27, 2025.

Students asked me to simplify robotics.

I figured — why stop there?

Let’s simplify robotics, AI, and self-driving cars all at once.

Here’s the punchline: It all comes down to probability — or, more formally, Markov Chains.

Think about it. When you type into ChatGPT, it predicts the most likely next word or sentence based on what you’ve typed. That’s probability in action.

Same with robots. Take Spot — the legged robot from Boston Dynamics. It uses sensor data to understand its body position, terrain profile, and target position — then predicts its next move. One foot after the other. 

Again: probability.

Same with self-driving cars. They perceive the environment — the road, traffic conditions, and status of traffic lights— and predict the next move of all agents in the scene. What will that truck do? Is that pedestrian going to cross the street? 

Again: probability.

If you’re an engineer, you probably use more technical i.e. "feel-good-on-the-resume" terms to hyperinflate probability. 

And that’s fair. We’ve all been there.

In the world of legged robotics, we talk about  “locomotion” and “navigation.” 

What we’re really doing is collecting data from sensors, estimating the terrain profile, and choosing a gait — crawl, walk, trot — often using model predictive control (MPC) or reinforcement learning. This is just a fancy way of saying how the robot moves its legs to stay balanced and get from A to B by continuously predicting what comes next on its path. 

Fancy words. Same core idea: predict, decide, act.

In the world of self-driving cars, we call it "perception, localization, path planning, motion control." But again — sensors enable us to perceive the world, filters like Kalman fuse the data, AI models predict future states of all agents in the scene, and then they decide how to steer next.

So what’s the common thread?

Prediction. And prediction is just "probability".

And that’s why systems like AI chatbots can hallucinate. They aren’t wired to REALITY. They’re wired to PROBABILITY. That’s not always the same thing.

Probability ≠ Truth.

But it's often close enough to act on.

Hope this made things a little clearer. That's how we teach here at Boring Sage.

Cheers,

Prathamesh

Disclaimer: This blog is for educational purposes only and does not constitute financial, business, or legal advice. The experiences shared are based on past events. All opinions expressed are those of the author and do not represent the views of any mentioned companies. Readers are solely responsible for conducting their own due diligence and should seek professional legal or financial advice tailored to their specific circumstances. The author and publisher make no representations or warranties regarding the accuracy of the content and expressly disclaim any liability for decisions made or actions taken based on this blog.