Geometric perception

(part 3)

MIT 6.800/6.843:

Robotic Manipulation

Fall 2021, Lecture 7

Follow live at https://slides.com/d/m9tZVh8/live

(or later at https://slides.com/russtedrake/fall21-lec07)

prog = MathematicalProgram()
# x is a symbolic variable
x = prog.NewContinuousVariables(2)

# numerical, pass in the coefficients:
# x'Qx + b'x + c
prog.AddQuadraticCost(Q, b, c, x)

# symbolic:
prog.AddCost(x.dot(x))
prog.AddQuadraticCost(x.dot(x))

# autodiff:
def my_cost(x):
	return x.dot(x)
prog.AddCost(my_cost, x)

# Adding autodiff costs/constraints => Solve(prog) will 
# pick a nonlinear optimization solver

DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation

Jeong Joon Park, Peter Florence, Julian Straub, Richard Newcombe, Steven Lovegrove

Lecture 7: Geometric Perception (part 3)

By russtedrake

Lecture 7: Geometric Perception (part 3)

MIT Robotic Manipulation Fall 2020 http://manipulation.csail.mit.edu

  • 720