Human Intention Inference Research Articles

SHARP: Shielding-Aware Robust Planning for Safe and Efficient Human-Robot Interaction

Jointly achieving safety and efficiency in human-robot interaction settings is a challenging problem, as the robot’s planning objectives may be at odds with the human’s own intent and expectations. Recent approaches ensure safe robot operation in uncertain environments through a supervisory control scheme, sometimes called “shielding,” which overrides the robot’s nominal plan with a safety fallback strategy when a safety-critical event is imminent. These reactive “last-resort” strategies (typically in the form of aggressive emergency maneuvers) focus on preserving safety without efficiency considerations; when the nominal planner is unaware of possible safety overrides, shielding can be activated more frequently than necessary, leading to degraded performance. In this letter, we propose a new shielding-based planning approach that allows the robot to plan efficiently by explicitly accounting for possible future shielding events. Leveraging recent work on Bayesian human motion prediction, the resulting robot policy proactively balances nominal performance with the risk of high-cost emergency maneuvers triggered by low-probability human behaviors. We formalize Shielding-Aware Robust Planning (SHARP) as a stochastic optimal control problem and propose a computationally efficient framework for finding tractable approximate solutions at runtime. Our method outperforms the shielding-agnostic motion planning baseline (equipped with the same human intent inference scheme) on simulated driving examples with human trajectories taken from the recently released Waymo Open Motion Dataset.

Autonomous Bayesian escorting of a human integrating intention and obstacle avoidance

AbstractThis paper presents a Bayesian technique for navigating a mobile robot to safely escort a human to their destination. A mathematical analysis of escorting identifies the significance of human intention inference for escorting success. The proposed Bayesian technique observes the head pose of the human walking behind the robot to infer their intention. The future human pose is then predicted by fusing two independent predictions using Gaussian fusion. One prediction method uses the observed intention, and the other prediction uses a physics‐based model. Both prediction methods initially use particle filters to best model nonlinear and non‐Gaussian motion. The robot goal pose is determined from the predicted human motion and adjusted if necessary leveraging the unoccupied distance map to avoid obstacles and successfully and safely enable autonomous escorting. Experimental analysis shows that the incorporation of the proposed human intention model reduces human position prediction error by approximately 33% when turning, improving escorting accuracy by 50%. The incorporation of the proposed obstacle avoidance has further demonstrated its need and efficacy for successful and safe autonomous escorting.

Human Intention Estimation using Fusion of Pupil and Hand Motion

This paper addresses the problem of human intention inference in the context of human-robot collaboration by fusing information from both hand motion obtained using skeletal tracking and eye gaze obtained using pupil tracking to predict a human’s current intention. Intention is modeled as a motion profile that converges to a goal location. A Kalman filter is used on eye gaze data to obtain gaze point estimates. The gaze estimates are transformed into a reference frame common to the hand data. An IMM filter that tracks hand motion is designed which takes advantage of the gaze filter’s model probabilities by fusing them with its own. The fusion is performed with user chosen parameters that determine the degree to which each filter’s predictions are weighed over time. An experiment is designed to show the utility of the proposed algorithm in a setting in which multiple reaching tasks are completed in an unknown order. The results show that the proposed algorithm can accurately predict the human’s intention before the tasks are completed.

Gaze and motion information fusion for human intention inference

An algorithm, named gaze-based multiple model intention estimator (G-MMIE), is presented for early prediction of the goal location (intention) of human reaching actions. The trajectories of the arm motion for reaching tasks are modeled by using an autonomous dynamical system with contracting behavior towards the goal location. To represent the dynamics of human arm reaching motion, a neural network (NN) is used. The parameters of the NN are learned under constraints derived based on contraction analysis. The constraints ensure that the trajectories of the dynamical system converge to a single equilibrium point. In order to use the motion model learned from a few demonstrations in new scenarios with multiple candidate goal locations, an interacting multiple-model (IMM) framework is used. For a given reaching motion, multiple models are obtained by translating the equilibrium point of the contracting system to different known candidate locations. Hence, each model corresponds to the reaching motion that ends at the respective candidate location. Further, since humans tend to look toward the location they are reaching for, prior probabilities of the goal locations are calculated based on the information about the human’s gaze. The posterior probabilities of the models are calculated through interacting model matched filtering. The candidate location with the highest posterior probability is chosen to be the estimate of the true goal location. Detailed quantitative evaluations of the G-MMIE algorithm on two different datasets involving 15 subjects, and comparisons with state-of-the-art intention inference algorithms are presented.

Fuzzy context-specific intention inference for robotic caregiving

To provide timely and appropriate assistance, robots must have the capability of proactively understanding a user’s personal needs, the so-called human intention inference. In human–human interaction, humans have a natural and implicit way to infer others’ intentions by selecting correlated context features and interpreting these features based on their life experience. However, robots do not have this capability and it is not realistic to build an explicit formula to associate human intentions with context. In this article, a novel fuzzy context-specific intention inference method is developed for human-like implicit human intention inference. With a fuzzy manner, context features are converted into discrete context statuses, which are similar to human subjective feelings. An intention-centered common sense database is developed consisting of correlated fuzzy context statuses, object affordances, and their relationship with human intentions. With this database, a Fuzzy Naïve Bayesian Network algorithm is adopted for implicit intention inference. Home scenario results validated the fuzzy context-specific intention inference methods reliability and lab scenario results validated the fuzzy context-specific intention inference methods effectiveness and robustness. This work is expected to develop intuitive and effective human–robot interaction, consequently enhancing the adoption of assistive technologies and improving the independence of the disabled and elderly in activities of daily living.