More Like this

1. MUTEX: Learning Unified Policies from Multimodal Task Specifications

   Shah, Rutav; Martín-Martín, Roberto; Zhu, Yuke (November 2023, Conference on Robot Learning)

   Humans use different modalities, such as speech, text, images, videos, etc., to communicate their intent and goals with teammates. For robots to become better assistants, we aim to endow them with the ability to follow instructions and understand tasks specified by their human partners. Most robotic policy learning methods have focused on one single modality of task specification while ignoring the rich cross-modal information. We present MUTEX, a unified approach to policy learning from multimodal task specifications. It trains a transformer-based architecture to facilitate cross-modal reasoning, combining masked modeling and cross-modal matching objectives in a two-stage training procedure. After training, MUTEX can follow a task specification in any of the six learned modalities (video demonstrations, goal images, text goal descriptions, text instructions, speech goal descriptions, and speech instructions) or a combination of them. We systematically evaluate the benefits of MUTEX in a newly designed dataset with 100 tasks in simulation and 50 tasks in the real world, annotated with multiple instances of task specifications in different modalities, and observe improved performance over methods trained specifically for any single modality. 

   more » « less
2. Human mobile robot interaction in the retail environment

   https://doi.org/10.1038/s41597-022-01802-8  

   Chen, Yuhao; Luo, Yue; Yang, Chizhao; Yerebakan, Mustafa Ozkan; Hao, Shuai; Grimaldi, Nicolas; Li, Song; Hayes, Read; Hu, Boyi (November 2022, Scientific Data)

   Abstract As technology advances, Human-Robot Interaction (HRI) is boosting overall system efficiency and productivity. However, allowing robots to be present closely with humans will inevitably put higher demands on precise human motion tracking and prediction. Datasets that contain both humans and robots operating in the shared space are receiving growing attention as they may facilitate a variety of robotics and human-systems research. Datasets that track HRI with rich information other than video images during daily activities are rarely seen. In this paper, we introduce a novel dataset that focuses on social navigation between humans and robots in a future-oriented Wholesale and Retail Trade (WRT) environment (https://uf-retail-cobot-dataset.github.io/). Eight participants performed the tasks that are commonly undertaken by consumers and retail workers. More than 260 minutes of data were collected, including robot and human trajectories, human full-body motion capture, eye gaze directions, and other contextual information. Comprehensive descriptions of each category of data stream, as well as potential use cases are included. Furthermore, analysis with multiple data sources and future directions are discussed. 

   more » « less
3. Hierarchical Task Learning from Language Instructions with Unified Transformers and Self-Monitoring

   https://doi.org/10.18653/v1/2021.findings-acl.368  

   Zhang, Yichi; Chai, Joyce (January 2021, ACL 2021, Findings.)

   Despite recent progress, learning new tasks through language instructions remains an extremely challenging problem. On the ALFRED benchmark for task learning, the published state-of-the-art system only achieves a task success rate of less than 10% in an unseen environment, compared to the human performance of over 90%. To address this issue, this paper takes a closer look at task learning. In a departure from a widely applied end-to-end architecture, we decomposed task learning into three sub-problems: sub-goal planning, scene navigation, and object manipulation; and developed a model HiTUT1 (stands for Hierarchical Tasks via Unified Transformers) that addresses each sub-problem in a unified manner to learn a hierarchical task structure. On the ALFRED benchmark, HiTUT has achieved the best performance with a remarkably higher generalization ability. In the unseen environment, HiTUT achieves over 160% performance gain in success rate compared to the previous state of the art. The explicit representation of task structures also enables an in-depth understanding of the nature of the problem and the ability of the agent, which provides insight for future benchmark development and evaluation. 

   more » « less
4. Autonomous Robot Goal Seeking and Collision Avoidance in the Physical World: An Automated Learning and Evaluation Framework Based on the PPO Method

   https://doi.org/10.3390/app142311020  

   Cheng, Wen-Chung; Ni, Zhen; Zhong, Xiangnan; Wei, Minghan (November 2024, Applied Sciences)

   Mobile robot navigation is a critical aspect of robotics, with applications spanning from service robots to industrial automation. However, navigating in complex and dynamic environments poses many challenges, such as avoiding obstacles, making decisions in real-time, and adapting to new situations. Reinforcement Learning (RL) has emerged as a promising approach to enable robots to learn navigation policies from their interactions with the environment. However, application of RL methods to real-world tasks such as mobile robot navigation, and evaluating their performance under various training–testing settings has not been sufficiently researched. In this paper, we have designed an evaluation framework that investigates the RL algorithm’s generalization capability in regard to unseen scenarios in terms of learning convergence and success rates by transferring learned policies in simulation to physical environments. To achieve this, we designed a simulated environment in Gazebo for training the robot over a high number of episodes. The training environment closely mimics the typical indoor scenarios that a mobile robot can encounter, replicating real-world challenges. For evaluation, we designed physical environments with and without unforeseen indoor scenarios. This evaluation framework outputs statistical metrics, which we then use to conduct an extensive study on a deep RL method, namely the proximal policy optimization (PPO). The results provide valuable insights into the strengths and limitations of the method for mobile robot navigation. Our experiments demonstrate that the trained model from simulations can be deployed to the previously unseen physical world with a success rate of over 88%. The insights gained from our study can assist practitioners and researchers in selecting suitable RL approaches and training–testing settings for their specific robotic navigation tasks. 

   more » « less
5. A Large Model’s Ability to Identify 3D Objects as a Function of Viewing Angle

   https://doi.org/10.1109/AIxVR59861.2024.00006  

   Rubinstein, Jacob; Ferraro, Francis; Matuszek, Cynthia; Engel, Don (January 2024, Proceedings of the IEEE Artificial Intelligence x Virtual Reality (AIxVR) Conference)

   Virtual reality is progressively more widely used to support embodied AI agents, such as robots, which frequently engage in ‘sim-to-real’ based learning approaches. At the same time, tools such as large vision-and-language models offer new capabilities that tie into a wide variety of tasks and capabilities. In order to understand how such agents can learn from simulated environments, we explore a language model’s ability to recover the type of object represented by a photorealistic 3D model as a function of the 3D perspective from which the model is viewed. We used photogrammetry to create 3D models of commonplace objects and rendered 2D images of these models from an fixed set of 420 virtual camera perspectives. A well-studied image and language model (CLIP) was used to generate text (i.e., prompts) corresponding to these images. Using multiple instances of various object classes, we studied which camera perspectives were most likely to return accurate text categorizations for each class of object. 

   more » « less