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

• URL: http://arxiv.org/abs/2002.00941v2
• Date: Fri, 28 Feb 2020 23:59:41 GMT
• Title: Quantifying Hypothesis Space Misspecification in Learning from Human-Robot Demonstrations and Physical Corrections
• Authors: Andreea Bobu, Andrea Bajcsy, Jaime F. Fisac, Sampada Deglurkar, Anca D. Dragan
• Abstract summary: Recent work focuses on how robots can use such input to learn intended objectives. We demonstrate our method on a 7 degree-of-freedom robot manipulator in learning from two important types of human input.
• Score: 34.53709602861176
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Learning Object Properties Using Robot Proprioception via Differentiable Robot-Object Interaction [52.12746368727368]
  Differentiable simulation has become a powerful tool for system identification. Our approach calibrates object properties by using information from the robot, without relying on data from the object itself. We demonstrate the effectiveness of our method on a low-cost robotic platform.
  arXiv  Detail & Related papers  (2024-10-04T20:48:38Z)
• Guessing human intentions to avoid dangerous situations in caregiving robots [1.3546242205182986]
  We propose an algorithm that detects risky situations for humans, selecting a robot action that removes the danger in real time. We use the simulation-based approach to ATM and adopt the 'like-me' policy to assign intentions and actions to people. The algorithm has been implemented as part of an existing cognitive architecture and tested in simulation scenarios.
  arXiv  Detail & Related papers  (2024-03-24T20:43:29Z)
• SACSoN: Scalable Autonomous Control for Social Navigation [62.59274275261392]
  We develop methods for training policies for socially unobtrusive navigation. By minimizing this counterfactual perturbation, we can induce robots to behave in ways that do not alter the natural behavior of humans in the shared space. We collect a large dataset where an indoor mobile robot interacts with human bystanders.
  arXiv  Detail & Related papers  (2023-06-02T19:07:52Z)
• Aligning Robot and Human Representations [50.070982136315784]
  We argue that current representation learning approaches in robotics should be studied from the perspective of how well they accomplish the objective of representation alignment. We mathematically define the problem, identify its key desiderata, and situate current methods within this formalism.
  arXiv  Detail & Related papers  (2023-02-03T18:59:55Z)
• Learning Reward Functions for Robotic Manipulation by Observing Humans [92.30657414416527]
  We use unlabeled videos of humans solving a wide range of manipulation tasks to learn a task-agnostic reward function for robotic manipulation policies. The learned rewards are based on distances to a goal in an embedding space learned using a time-contrastive objective.
  arXiv  Detail & Related papers  (2022-11-16T16:26:48Z)
• Robots with Different Embodiments Can Express and Influence Carefulness in Object Manipulation [104.5440430194206]
  This work investigates the perception of object manipulations performed with a communicative intent by two robots. We designed the robots' movements to communicate carefulness or not during the transportation of objects.
  arXiv  Detail & Related papers  (2022-08-03T13:26:52Z)
• Explain yourself! Effects of Explanations in Human-Robot Interaction [10.389325878657697]
  Explanations of robot decisions could affect user perceptions, justify their reliability, and increase trust. The effects on human perceptions of robots that explain their decisions have not been studied thoroughly. This study demonstrates the need for and potential of explainable human-robot interaction.
  arXiv  Detail & Related papers  (2022-04-09T15:54:27Z)
• AAAI SSS-22 Symposium on Closing the Assessment Loop: Communicating Proficiency and Intent in Human-Robot Teaming [4.787322716745613]
  How should a robot convey predicted ability on a new task? How should a robot adapt its proficiency criteria based on human intentions and values? There are no agreed upon standards for evaluating proficiency and intent-based interactions.
  arXiv  Detail & Related papers  (2022-04-05T18:28:01Z)
• Reasoning about Counterfactuals to Improve Human Inverse Reinforcement Learning [5.072077366588174]
  Humans naturally infer other agents' beliefs and desires by reasoning about their observable behavior. We propose to incorporate the learner's current understanding of the robot's decision making into our model of human IRL. We also propose a novel measure for estimating the difficulty for a human to predict instances of a robot's behavior in unseen environments.
  arXiv  Detail & Related papers  (2022-03-03T17:06:37Z)
• Human Grasp Classification for Reactive Human-to-Robot Handovers [50.91803283297065]
  We propose an approach for human-to-robot handovers in which the robot meets the human halfway. We collect a human grasp dataset which covers typical ways of holding objects with various hand shapes and poses. We present a planning and execution approach that takes the object from the human hand according to the detected grasp and hand position.
  arXiv  Detail & Related papers  (2020-03-12T19:58:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.