Probabilistic Human Intent Recognition for Shared Autonomy in Assistive Robotics

By Siddarth Jain, Brenna D. Argall. 2019

137 citations recorded by the source corpus.

Effective human-robot collaboration in shared autonomy requires reasoning about the intentions of the human partner. To provide meaningful assistance, the autonomy has to first correctly predict, or infer, the intended goal of the human collaborator. In this work, we present a mathematical formulation for intent inference during assistive teleoperation under shared autonomy. Our recursive Bayesian filtering approach models and fuses multiple non-verbal observations to probabilistically reason about the intended goal of the user without explicit communication. In addition to contextual observations, we model and incorporate the human agent’s behavior as goal-directed actions with adjustable rationality to inform intent recognition. Furthermore, we introduce a user-customized optimization of this adjustable rationality to achieve user personalization. We validate our approach with a human subjects study that evaluates intent inference performance under a variety of goal scenarios and tasks. Importantly, the studies are performed using multiple control interfaces that are typically available to users in the assistive domain, which differ in the continuity and dimensionality of the issued control signals. The implications of the control interface limitations on intent inference are analyzed. The study results show that our approach in many scenarios outperforms existing solutions for intent inference in assistive teleoperation and otherwise performs comparably. Our findings demonstrate the benefit of probabilistic modeling and the incorporation of human agent behavior as goal-directed actions where the adjustable rationality model is user customized. Results further show that the underlying intent inference approach directly affects shared autonomy performance, as do control interface limitations.

Subfields: Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Reinforcement Learning

Citations in the corpus

LILA: Language-Informed Latent Actions (2021, methodology): “We build LILA within a shared autonomy framework [2, 16], applied to assistive teleoperation [17, 18].”
Shared Autonomy with Learned Latent Actions (2020, background): “Shared autonomy can make eating tasks easier by predicting the human’s intent and then augmenting their input [16, 8, 15].”
Learning latent actions to control assistive robots (2021, unknown): “But how do we combine this learned mapping with control theory to ensure that the human can accurately complete their desired task? Prior work on assistive arms leverages shared autonomy, where the robot’s action is a combination of the human’s input and autonomous assistance [16,25,24,7].”
Learning Visually Guided Latent Actions for Assistive Teleoperation (2021, methodology): “We build our approach atop a long-line of work around dimensionality reduction for assistive teleoperation (Ciocarlie and Allen, 2009; Jain and Argall, 2019) – including prior work on visually-guided manipulation and learned latent actions (Losey et al., 2020; Jeon et al., 2020; Li et al., 2020).”