We introduce GeoSACS, a geometric framework for shared autonomy (SA). In variable environments, SA methods can be used to combine robotic capabilities with real-time human input in a way that offloads the physical task from the human. To remain intuitive, it can be helpful to simplify requirements for human input (i.e., reduce the dimensionality), which create challenges for to map low-dimensional human inputs to the higher dimensional control space of robots without requiring large amounts of data. We built GeoSACS on canal surfaces, a geometric framework that represents potential robot trajectories as a canal from as few as two demonstrations. GeoSACS maps user corrections on the cross-sections of this canal to provide an efficient SA framework. We extend canal surfaces to consider orientation and update the control frames to support intuitive mapping from user input to robot motions. Finally, we demonstrate GeoSACS in two preliminary studies, including a complex manipulation task where a robot loads laundry into a washer.
Gaze following and social gaze prediction are fundamental tasks providing insights into human communication behaviors, intent, and social interactions. Most previous approaches addressed these tasks separately, either by designing highly specialized social gaze models that do not generalize to other social gaze tasks or by considering social gaze inference as an ad-hoc post-processing of the gaze following task. Furthermore, the vast majority of gaze following approaches have proposed static models that can handle only one person at a time, therefore failing to take advantage of social interactions and temporal dynamics. In this paper, we address these limitations and introduce a novel framework to jointly predict the gaze target and social gaze label for all people in the scene. The framework comprises of: (i) a temporal, transformer-based architecture that, in addition to image tokens, handles person-specific tokens capturing the gaze information related to each individual; (ii) a new dataset, VSGaze, that unifies annotation types across multiple gaze following and social gaze datasets. We show that our model trained on VSGaze can address all tasks jointly, and achieves state-of-the-art results for multi-person gaze following and social gaze prediction.
Gaze is a powerful form of non-verbal communication and social interaction that humans develop from an early age. As such, modeling this behavior is an important task that can benefit a broad set of application domains ranging from robotics to sociology. In particular, Gaze Following is defined as the prediction of the pixel-wise 2D location where a person in the image is looking. Prior efforts in this direction have focused primarily on CNN-based architectures to perform the task. In this paper, we introduce a novel transformer-based architecture for 2D gaze prediction. We experiment with 2 variants: the first one retains the same task formulation of predicting a gaze heatmap for one person at a time, while the second one casts the problem as a 2D point regression and allows us to perform multi-person gaze prediction with a single forward pass. This new architecture achieves state-of-the-art results on the GazeFollow and VideoAttentionTarget datasets. The code for this paper will be made publicly available.
Predicting where a person is looking is a complex task, requiring to understand not only the person's gaze and scene content, but also the 3D scene structure and the person's situation (are they manipulating? interacting or observing others? attentive?) to detect obstructions in the line of sight or apply attention priors that humans typically have when observing others. In this paper, we hypothesize that identifying and leveraging such priors can be better achieved through the exploitation of explicitly derived multimodal cues such as depth and pose. We thus propose a modular multimodal architecture allowing to combine these cues using an attention mechanism. The architecture can naturally be exploited in privacy-sensitive situations such as surveillance and health, where personally identifiable information cannot be released. We perform extensive experiments on the GazeFollow and VideoAttentionTarget public datasets, obtaining state-of-the-art performance and demonstrating very competitive results in the privacy setting case.
Gaze behaviors such as eye-contact or shared attention are important markers for diagnosing developmental disorders in children. While previous studies have looked at some of these elements, the analysis is usually performed on private datasets and is restricted to lab settings. Furthermore, all publicly available gaze target prediction benchmarks mostly contain instances of adults, which makes models trained on them less applicable to scenarios with young children. In this paper, we propose the first study for predicting the gaze target of children and interacting adults. To this end, we introduce the ChildPlay dataset: a curated collection of short video clips featuring children playing and interacting with adults in uncontrolled environments (e.g. kindergarten, therapy centers, preschools etc.), which we annotate with rich gaze information. We further propose a new model for gaze target prediction that is geometrically grounded by explicitly identifying the scene parts in the 3D field of view (3DFoV) of the person, leveraging recent geometry preserving depth inference methods. Our model achieves state of the art results on benchmark datasets and ChildPlay. Furthermore, results show that looking at faces prediction performance on children is much worse than on adults, and can be significantly improved by fine-tuning models using child gaze annotations. Our dataset and models will be made publicly available.
We propose to leverage Transformer architectures for non-autoregressive human motion prediction. Our approach decodes elements in parallel from a query sequence, instead of conditioning on previous predictions such as instate-of-the-art RNN-based approaches. In such a way our approach is less computational intensive and potentially avoids error accumulation to long term elements in the sequence. In that context, our contributions are fourfold: (i) we frame human motion prediction as a sequence-to-sequence problem and propose a non-autoregressive Transformer to infer the sequences of poses in parallel; (ii) we propose to decode sequences of 3D poses from a query sequence generated in advance with elements from the input sequence;(iii) we propose to perform skeleton-based activity classification from the encoder memory, in the hope that identifying the activity can improve predictions;(iv) we show that despite its simplicity, our approach achieves competitive results in two public datasets, although surprisingly more for short term predictions rather than for long term ones.
Humans effortlessly solve pushing tasks in everyday life but unlocking these capabilities remains a challenge in robotics because physics models of these tasks are often inaccurate or unattainable. State-of-the-art data-driven approaches learn to compensate for these inaccuracies or replace the approximated physics models altogether. Nevertheless, approaches like Deep Q-Networks (DQNs) suffer from local optima in large state-action spaces. Furthermore, they rely on well-chosen deep learning architectures and learning paradigms. In this paper, we propose to frame the learning of pushing policies (where to push and how) by DQNs as an image-to-image translation problem and exploit an Hourglass-based architecture. We present an architecture combining a predictor of which pushes lead to changes in the environment with a state-action value predictor dedicated to the pushing task. Moreover, we investigate positional information encoding to learn position-dependent policy behaviors. We demonstrate in simulation experiments with a UR5 robot arm that our overall architecture helps the DQN learn faster and achieve higher performance in a pushing task involving objects with unknown dynamics.
We propose to leverage recent advances in reliable 2D pose estimation with Convolutional Neural Networks (CNN) to estimate the 3D pose of people from depth images in multi-person Human-Robot Interaction (HRI) scenarios. Our method is based on the observation that using the depth information to obtain 3D lifted points from 2D body landmark detections provides a rough estimate of the true 3D human pose, thus requiring only a refinement step. In that line our contributions are threefold. (i) we propose to perform 3D pose estimation from depth images by decoupling 2D pose estimation and 3D pose refinement; (ii) we propose a deep-learning approach that regresses the residual pose between the lifted 3D pose and the true 3D pose; (iii) we show that despite its simplicity, our approach achieves very competitive results both in accuracy and speed on two public datasets and is therefore appealing for multi-person HRI compared to recent state-of-the-art methods.
Although automatic gaze estimation is very important to a large variety of application areas, it is difficult to train accurate and robust gaze models, in great part due to the difficulty in collecting large and diverse data (annotating 3D gaze is expensive and existing datasets use different setups). To address this issue, our main contribution in this paper is to propose an effective approach to learn a low dimensional gaze representation without gaze annotations, which to the best of our best knowledge, is the first work to do so. The main idea is to rely on a gaze redirection network and use the gaze representation difference of the input and target images (of the redirection network) as the redirection variable. A redirection loss in image domain allows the joint training of both the redirection network and the gaze representation network. In addition, we propose a warping field regularization which not only provides an explicit physical meaning to the gaze representations but also avoids redirection distortions. Promising results on few-shot gaze estimation (competitive results can be achieved with as few as <=100 calibration samples), cross-dataset gaze estimation, gaze network pretraining, and another task (head pose estimation) demonstrate the validity of our framework.