# Robotics

Canonical URL: https://shipslides.com/d/technology-robotics
Raw viewer URL: https://content.shipslides.com/d/technology-robotics/raw
Category: Technology
Slides: 15
Updated: 2026-05-17T20:49:48.785Z
Tags: technology, robotics

## Summary

N.T.S. Key sections include: ROBOTICS — KINEMATICS, SOFTWARE, AUTONOMY, EMBODIMENT; What we mean by "robot"; Selected milestones; Forward and inverse kinematics; The Robot Operating System; Sensors and perception; From A* to MPC; The factory floor; Mobile autonomy; The hard problem.

## Slide Outline

1. ROBOTICS — KINEMATICS, SOFTWARE, AUTONOMY, EMBODIMENT
2. What we mean by "robot"
3. Selected milestones
4. Forward and inverse kinematics
5. The Robot Operating System
6. Sensors and perception
7. From A* to MPC
8. The factory floor
9. Mobile autonomy
10. The hard problem
11. The humanoid wave
12. Learning + physics
13. Glossary
14. Recommended viewing
15. Open problems

## Slide Transcript

### Slide 1: ROBOTICS — KINEMATICS, SOFTWARE, AUTONOMY, EMBODIMENT

- BLUEPRINT · DECK 05 · ROBOTICS
- DRAFT — 2026-05-03
- SCALE
- N.T.S.
- SHEET
- A1 / 14
- DRAWN
- K.N.
- PROJECT
- VOL.II / 05

### Slide 2: What we mean by "robot"

- A robot is a programmable physical system that senses, plans, and acts. The word was coined by Karel Čapek's brother Josef for the 1920 play R.U.R., from the Czech robota (forced labor). Practical robotics dates from the 1954 patent of the first programmable manipulator by George Devol — the Unimate, deployed at GM in 1961 to handle die-cast parts.

### Slide 3: Selected milestones

- YearEvent
- 1954Devol patents the programmable manipulator (US 2,988,237).
- 1961Unimate at GM Trenton — first industrial robot deployment.
- 1969Stanford Arm; Shakey at SRI — first mobile reasoning robot.
- 1973KUKA Famulus — first electrically driven 6-axis arm.
- 1986Honda E0 walking research begins (leading to ASIMO, 2000).
- 2002iRobot Roomba ships — domestic robotics at scale.
- 2004DARPA Grand Challenge (no winner). 2005: Stanford's Stanley wins.
- 2007ROS development begins at Willow Garage.
- 2013Boston Dynamics Atlas v1 unveiled.
- 2020sDeep RL + transformers reach manipulation; Tesla Optimus, Figure 01, 1X NEO.

### Slide 4: Forward and inverse kinematics

- The Denavit–Hartenberg convention encodes each joint with four parameters (a, α, d, θ) and chains 4×4 transforms.
- T_base→tool = A_1 · A_2 · ... · A_n
- A_i = Rot_z(θ_i) · Trans_z(d_i) · Trans_x(a_i) · Rot_x(α_i)
- Inverse kinematics — solving for joint angles given a desired tool pose — is generically multi-solution and handled numerically (Newton-Raphson, damped least squares) or analytically for solvable manipulators.

### Slide 5: The Robot Operating System

- ROS (2007, Willow Garage; ROS 2 from 2017) is not an OS but a middleware: a graph of nodes communicating over named topics with publish/subscribe and request/response. It standardized perception, control, and SLAM stacks across labs and industry.
- # publish a velocity command (ROS 2, rclpy)
- import rclpy
- from geometry_msgs.msg import Twist
- rclpy.init()
- node = rclpy.create_node('drive')
- pub = node.create_publisher(Twist, '/cmd_vel', 10)
- msg = Twist(); msg.linear.x = 0.5; msg.angular.z = 0.2
- pub.publish(msg)

### Slide 6: Sensors and perception

- Cameras
- RGB, stereo, RGB-D (Kinect 2010), event cameras (DVS). Modern visual perception is dominated by deep CNNs and ViTs.
- LiDAR
- 360° rotating (Velodyne 2007), solid-state, FMCW. Backbone of autonomous vehicles for 3D mapping.
- IMU
- MEMS accelerometers + gyros provide proprioception; fused with vision (VIO) for pose estimation.
- Force/Torque
- Six-axis sensors at the wrist enable compliant assembly and contact-rich manipulation.

### Slide 7: From A* to MPC

- Classical motion planning: A*, Dijkstra, RRT/RRT*, PRM. Trajectory optimization (CHOMP, TrajOpt) treats the path as a continuous variable. Modern model-predictive control (MPC) and differentiable physics simulators have pulled planning toward learned dynamics.

### Slide 8: The factory floor

- The "big four" industrial robot makers — FANUC, Yaskawa, ABB, KUKA — together control most of the global market. Annual installations crossed 600,000 units in 2024 (IFR). Collaborative robots ("cobots") from Universal Robots (2008) opened lower-payload, fenceless deployment.
- ClassPayloadSpeedUse
- SCARA~3–10 kgfastpick & place, electronics
- 6-axis articulated~5–500 kgmediumwelding, palletizing, painting
- Delta~1 kgvery fastfood sorting, packaging
- Cobot~3–16 kgslowassembly, lab, light assembly

### Slide 9: Mobile autonomy

- The 2005 DARPA Grand Challenge — Stanford's "Stanley" finishing 132 mi of desert in 6h54m — kicked off the modern self-driving stack: HD maps, multi-modal perception, behavior prediction, and safety cases.
- Waymo opened robotaxi service in Phoenix in 2018 and reported 250,000+ weekly paid rides across multiple cities by May 2025. Cruise withdrew its San Francisco service in late 2023 after a serious incident.
- As of 2026, fully driverless commercial service exists in Phoenix, San Francisco, Los Angeles, Austin, and several Chinese cities (Beijing, Wuhan).

### Slide 10: The hard problem

- Locomotion looks superhuman; manipulation lags. Real-world objects are partially observable, deformable, and friction-dependent. Recent advances:
- Learning from demonstration — RT-1, RT-2, OpenVLA tie vision-language models to action.
- Diffusion policies (Chi et al., 2023) sample trajectories conditioned on observations.
- Tactile sensing — GelSight, DIGIT, BioTac.
- Sim-to-real with domain randomization (Tobin 2017) and large-scale parallel sim (Isaac Gym, MuJoCo MJX).

### Slide 11: The humanoid wave

- 2022–2026 saw a sudden glut of bipedal humanoids: Tesla Optimus, Figure 01/02, 1X NEO, Apptronik Apollo, Unitree H1, Boston Dynamics' electric Atlas (2024). Drivers: cheap actuators, learned whole-body control, and a labor-shortage thesis in logistics and manufacturing.

### Slide 12: Learning + physics

- RL in simulation now drives many real-world locomotion controllers (ANYmal, Spot, humanoids). The recipe: massive parallelization in GPU-accelerated simulators, randomize physics, distill to a small policy network, deploy on-robot.
- # conceptual
- for step in range(10**9):
- obs = sim.get_obs()
- a = policy(obs)
- obs2, r = sim.step(a)
- buffer.add(obs, a, r, obs2)
- if step % K == 0: ppo_update(policy, buffer)

### Slide 13: Glossary

- TermMeaning
- DOFDegrees of freedom — independent joint axes.
- SLAMSimultaneous localization and mapping.
- URDFUnified Robot Description Format — XML model of a robot.
- ComplianceYielding to external force; opposite of stiffness.
- End-effectorThe tool at the last link of a manipulator.

### Slide 14: Recommended viewing

- Watch: robotics manipulation research

### Slide 15: Open problems

- General-purpose dexterity at human-hand level cost and reliability.
- Robust long-horizon autonomy without expensive teleoperation fallback.
- Safe physical HRI in unstructured human environments.
- Battery energy density limiting humanoid runtime to a few hours.
- A common "ImageNet of manipulation" for learning at scale.


## Related Decks

- [AI & Machine Learning](https://shipslides.com/d/technology-ai-and-ml)
- [Artificial Intelligence: From Turing to Transformers](https://shipslides.com/d/technology-artificial-intelligence)
- [Biotechnology](https://shipslides.com/d/technology-biotech)
- [Blockchain Technology](https://shipslides.com/d/technology-blockchain)