More Like this

1. Collaborative Semantic Data Fusion with Dynamically Observable Decision Processes

   Burks, L. ; Ahmed, N. ( February 2020 , 2019 22th International Conference on Information Fusion (FUSION))

   null (Ed.)

   This work presents novel techniques for tightly integrated online information fusion and planning in human-autonomy teams operating in partially known environments. Motivated by dynamic target search problems, we present a new map-based sketch interface for online soft-hard data fusion. This interface lets human collaborators efficiently update map information and continuously build their own highly flexible ad hoc dictionaries for making language-based semantic observations, which can be actively exploited by autonomous agents in optimal search and information gathering problems. We formally link these capabilities to POMDP algorithms for optimal planning under uncertainty, and develop a new Dynamically Observable Monte Carlo planning (DOMCP) algorithm as an efficient means for updating online sampling-based planning policies for POMDPs with non-static observation models. DOMCP is validated on a small scale robot localization problem, and then demonstrated with our new user interface on a simulated dynamic target search scenario in a partially known outdoor environment. 

   more » « less
2. Activity recognition in wearables using adversarial multi-source domain adaptation

   https://doi.org/https://doi.org/10.1016/j.smhl.2020.100174  

   Chakma, A ; Faridee, A ; Khan, H ; Roy, N ( March 2021 , Smart health)

   null (Ed.)

   Human activity recognition (HAR) from wearable sensors data has become ubiquitous due to the widespread proliferation of IoT and wearable devices. However, recognizing human activity in heterogeneous environments, for example, with sensors of different models and make, across different persons and their on-body sensor placements introduces wide range discrepancies in the data distributions, and therefore, leads to an increased error margin. Transductive transfer learning techniques such as domain adaptation have been quite successful in mitigating the domain discrepancies between the source and target domain distributions without the costly target domain data annotations. However, little exploration has been done when multiple distinct source domains are present, and the optimum mapping to the target domain from each source is not apparent. In this paper, we propose a deep Multi-Source Adversarial Domain Adaptation (MSADA) framework that opportunistically helps select the most relevant feature representations from multiple source domains and establish such mappings to the target domain by learning the perplexity scores. We showcase that the learned mappings can actually reflect our prior knowledge on the semantic relationships between the domains, indicating that MSADA can be employed as a powerful tool for exploratory activity data analysis. We empirically demonstrate that our proposed multi-source domain adaptation approach achieves 2% improvement with OPPORTUNITY dataset (cross-person heterogeneity, 4 ADLs), whereas 13% improvement on DSADS dataset (cross-position heterogeneity, 10 ADLs and sports activities). 

   more » « less
3. Bootstrapping Motor Skill Learning with Motion Planning

   https://doi.org/10.1109/IROS51168.2021.9636661  

   Abbatematteo, B ; Rosen, E ; Tellex, S ; Konidaris, G.D. ( September 2021 , Proceedings of the 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems)

   Learning a robot motor skill from scratch is impractically slow; so much so that in practice, learning must typically be bootstrapped using human demonstration. However, relying on human demonstration necessarily degrades the autonomy of robots that must learn a wide variety of skills over their operational lifetimes. We propose using kinematic motion planning as a completely autonomous, sample efficient way to bootstrap motor skill learning for object manipulation. We demonstrate the use of motion planners to bootstrap motor skills in two complex object manipulation scenarios with different policy representations: opening a drawer with a dynamic movement primitive representation, and closing a microwave door with a deep neural network policy. We also show how our method can bootstrap a motor skill for the challenging dynamic task of learning to hit a ball off a tee, where a kinematic plan based on treating the scene as static is insufficient to solve the task, but sufficient to bootstrap a more dynamic policy. In all three cases, our method is competitive with human-demonstrated initialization, and significantly outperforms starting with a random policy. This approach enables robots to to efficiently and autonomously learn motor policies for dynamic tasks without human demonstration. 

   more » « less
4. Digging into semantics: Where do search-based software repair methods search?

   https://doi.org/10.1007/978-3-031-14721-0_1  

   Ahmad, H ; Cashin, P. ; Weimer, W. ; Forrest, S. ( September 2022 , Lecture notes in computer science)

   Rudolph, Günter ; Konova, Anna ; Aguirre, Hernán ; Kerschke, Pascal ; Ochoa, G. ; Tušar, Tea (Ed.)

   Search-based methods are a popular approach for automatically repairing software bugs, a field known as automated program repair (APR). There is increasing interest in empirical evaluation and comparison of different APR methods, typically measured as the rate of successful repairs on benchmark sets of buggy programs. Such evaluations, however, fail to explain why some approaches succeed and others fail. Because these methods typically use syntactic representations, i.e., source code, we know little about how the different methods explore their semantic spaces, which is relevant for assessing repair quality and understanding search dynamics. We propose an automated method based on program semantics, which provides quantitative and qualitative information about different APR search-based techniques. Our approach requires no manual annotation and produces both mathematical and human-understandable insights. In an empirical evaluation of 4 APR tools and 34 defects, we investigate the relationship between search-space exploration, semantic diversity and repair success, examining both the overall picture and how the tools’ search unfolds. Our results suggest that population diversity alone is not sufficient for finding repairs, and that searching in the right place is more important than searching broadly, highlighting future directions for the research community 

   more » « less
5. Reward Learning With Intractable Normalizing Functions

   https://doi.org/10.1109/LRA.2023.3320009  

   Hoegerman, Joshua ; Losey, Dylan ( November 2023 , IEEE Robotics and Automation Letters)

   Robots can learn to imitate humans by inferring what the human is optimizing for. One common framework for this is Bayesian reward learning, where the robot treats the human's demonstrations and corrections as observations of their underlying reward function. Unfortunately, this inference is doubly-intractable: the robot must reason over all the trajectories the person could have provided and all the rewards the person could have in mind. Prior work uses existing robotic tools to approximate this normalizer. In this letter, we group previous approaches into three fundamental classes and analyze the theoretical pros and cons of their approach. We then leverage recent research from the statistics community to introduce Double MH reward learning, a Monte Carlo method for asymptotically learning the human's reward in continuous spaces. We extend Double MH to conditionally independent settings (where each human correction is viewed as completely separate) and conditionally dependent environments (where the human's current correction may build on previous inputs). Across simulations and user studies, our proposed approach infers the human's reward parameters more accurately than the alternate approximations when learning from either demonstrations or corrections. 

   more » « less