Quantifying Hypothesis Space Misspecification in Learning from Human-Robot Demonstrations and Physical Corrections

02/03/2020
by   Andreea Bobu, et al.
0

Human input has enabled autonomous systems to improve their capabilities and achieve complex behaviors that are otherwise challenging to generate automatically. Recent work focuses on how robots can use such input - like demonstrations or corrections - to learn intended objectives. These techniques assume that the human's desired objective already exists within the robot's hypothesis space. In reality, this assumption is often inaccurate: there will always be situations where the person might care about aspects of the task that the robot does not know about. Without this knowledge, the robot cannot infer the correct objective. Hence, when the robot's hypothesis space is misspecified, even methods that keep track of uncertainty over the objective fail because they reason about which hypothesis might be correct, and not whether any of the hypotheses are correct. In this paper, we posit that the robot should reason explicitly about how well it can explain human inputs given its hypothesis space and use that situational confidence to inform how it should incorporate human input. We demonstrate our method on a 7 degree-of-freedom robot manipulator in learning from two important types of human input: demonstrations of manipulation tasks, and physical corrections during the robot's task execution.

READ FULL TEXT

page 2

page 6

page 8

page 12

page 13

page 14

page 16

page 21

research
10/11/2018

Learning under Misspecified Objective Spaces

Learning robot objective functions from human input has become increasin...
research
01/31/2019

Characterizing Input Methods for Human-to-robot Demonstrations

Human demonstrations are important in a range of robotics applications, ...
research
06/23/2020

Feature Expansive Reward Learning: Rethinking Human Input

In collaborative human-robot scenarios, when a person is not satisfied w...
research
03/09/2019

Literal or Pedagogic Human? Analyzing Human Model Misspecification in Objective Learning

It is incredibly easy for a system designer to misspecify the objective ...
research
04/19/2023

Applying Learning-from-observation to household service robots: three common-sense formulation

Utilizing a robot in a new application requires the robot to be programm...
research
01/13/2021

Top Program Construction and Reduction for polynomial time Meta-Interpretive Learning

Meta-Interpretive Learners, like most ILP systems, learn by searching fo...
research
02/11/2020

Human-to-Robot Attention Transfer for Robot Execution Failure Avoidance Using Stacked Neural Networks

Due to world dynamics and hardware uncertainty, robots inevitably fail i...

Please sign up or login with your details

Forgot password? Click here to reset