Tech Briefs Magazine - August 2022 - MD-16

complete several tasks. The researchers
tested the planner in scenarios where
humans and robots had to insert blocks
into a peg board and stack parts of different
shapes and sizes made of Lego bricks.
Using algorithms and software to decide
how to delegate and divide labor is
not new, even when robots are part of
the team. However, this work is among
the first to include robot learning in its
reasoning.
Often in manufacturing, a person will
manually manipulate a robotic arm to
teach the robot how to complete a task.
Teaching a robot takes time and, therefore,
has a high upfront cost. But it can
be beneficial in the long run if the robot
can learn a new skill. Part of the complexity
is deciding when it is best to teach a
robot versus delegating the task to a
human. This requires the robot to predict
what other tasks it can complete after
learning a new task.
Given this information, the planner
converts the problem into a mixed integer
program - an optimization program
commonly used in scheduling, production
planning or designing communication
networks - that can be solved
efficiently by off-the-shelf software. The
planner performed better than traditional
models in all instances and decreased the
cost of completing the tasks by 10 percent
to 15 percent.
For more information, contact
Robotics Institute researchers have developed an algorithmic planner that helps delegate tasks to humans and
robots. (Image: Carnegie Mellon University)
Aaron Aupperlee at 412-268-9068 or
aaupperlee@cmu.edu.
A New Method to Improve Motion Planning for Robots
Interactive program aids motion planning for environments with obstacles.
Rice University, Houston, TX
J
ust like us, robots can't see through
walls. Sometimes they need a little
help to get where they're going.
Engineers at Rice University have developed
a method that allows humans
to help robots " see " their environments
and carry out tasks.
The strategy called Bayesian Learning
IN the Dark (BLIND) is a novel solution
to the long-standing problem of
motion planning for robots that work
The task set for this Fetch robot by Rice University
computer scientists is made easier by their BLIND
software, which allows for human intervention when
the robot's path is blocked by an obstacle. Keeping
a human in the loop augments robot perception and
prevents the execution of unsafe motion. (Image:
Kavraki Lab/Rice University)
16
in environments where not everything
is clearly visible all the time.
The algorithm developed by Carlos
Quintero-Peña and Constantinos
Chamzas of Rice's George R. Brown
School of Engineering, both graduate
students working with computer scientists
Lydia Kavraki and Vaibhav Unhelkar,
keeps a human in the loop to augment
robot perception and, importantly, prevent
the execution of unsafe motion.
To do so, they combined Bayesian inverse
reinforcement learning (by which
a system learns from continually updated
information and experience) with established
motion planning techniques to assist
robots that have high degrees of freedom.
To test BLIND, the Rice lab directed
a Fetch robot, an articulated arm with
seven joints, to grab a small cylinder
from a table and move it to another, but
in doing so it had to move past a barrier.
" If you have more joints, instructions to
the robot are complicated, " QuinteroPeña
said. " If you're directing a human,
you can just say, 'Lift up your hand.' "
But a robot's programmers have to
be specific about the movement of each
joint at each point in its trajectory, especially
when obstacles block the machine's
" view " of its target.
Rather than programming a trajectory
up front, BLIND inserts a human
mid-process to refine the choreographed
options, or best guesses, suggested by
the robot's algorithm.
" BLIND allows
us to take information in the human's
head and compute our trajectories in
this high-degree-of-freedom space, "
Quintero-Peña said. " We use a specific
way of feedback called critique, basically
a binary form of feedback where the
human is given labels on pieces of the
trajectory, " he said.
These labels appear as connected
green dots that represent possible paths.
As BLIND steps from dot to dot, the
human approves or rejects each movement
to refine the path, avoiding obstacles
as efficiently as possible. The robot
uses this information to plan and once
rewarded with an approved set of movements,
it can carry out its task.
For more information, contact Mike
Williams at 713-348-6728 or mikewilliams@rice.edu.
Motion
Design, August 2022

Tech Briefs Magazine - August 2022

Table of Contents for the Digital Edition of Tech Briefs Magazine - August 2022