More Like this

1. Parameter-Free Segmentation of Robot Movements with Cross-Correlation Using Different Similarity Metrics

   Carvalho, Wendy; Elkoudi, Meriem; Hertel, Brendan; Azadeh, Reza (July 2025, IEEE; Ubiquitous Robots 2025)

   Often, robots are asked to execute primitive movements, whether as a single action or in a series of actions representing a larger, more complex task. These movements can be learned in many ways, but a common one is from demonstrations presented to the robot by a teacher. However, these demonstrations are not always simple movements themselves, and complex demonstrations must be broken down, or segmented, into primitive movements. In this work, we present a parameter-free approach to segmentation using techniques inspired by autocorrelation and cross-correlation from signal processing. In cross-correlation, a representative signal is found in some larger, more complex signal by correlating the representative signal with the larger signal. This same idea can be applied to segmenting robot motion and demonstrations provided with a representative motion primitive. This results in a fast and accurate segmentation, which does not take any parameters. One of the main contributions of this paper is modification of the cross-correlation process by employing similarity metrics that can capture features specific to robot movements. To validate our framework, we conduct several experiments of complex tasks both in simulation and in real world. We also evaluate the effectiveness of our segmentation framework by comparing various similarity metrics. 

   more » « less
2. Latent Action Space for Offline Reinforcement Learning

   Zhou, Wenxuan; Bajracharya, Sujay; Held, David (January 2020, Conference on Robot Learning)

   null (Ed.)

   The goal of offline reinforcement learning is to learn a policy from a fixed dataset, without further interactions with the environment. This setting will be an increasingly more important paradigm for real-world applications of reinforcement learning such as robotics, in which data collection is slow and potentially dangerous. Existing off-policy algorithms have limited performance on static datasets due to extrapolation errors from out-of-distribution actions. This leads to the challenge of constraining the policy to select actions within the support of the dataset during training. We propose to simply learn the Policy in the Latent Action Space (PLAS) such that this requirement is naturally satisfied. We evaluate our method on continuous control benchmarks in simulation and a deformable object manipulation task with a physical robot. We demonstrate that our method provides competitive performance consistently across various continuous control tasks and different types of datasets, outperforming existing offline reinforcement learning methods with explicit constraints. 

   more » « less
3. Learning to make decisions via submodular regularization

   Alieva, A.; Aceves, A.; Song, J.; Mayo, S.; Yue, Y.; Chen, Y. (October 2020,  International Conference on Learning Representations)

   Many sequential decision making tasks can be viewed as combinatorial optimiza- tion problems over a large number of actions. When the cost of evaluating an ac- tion is high, even a greedy algorithm, which iteratively picks the best action given the history, is prohibitive to run. In this paper, we aim to learn a greedy heuris- tic for sequentially selecting actions as a surrogate for invoking the expensive oracle when evaluating an action. In particular, we focus on a class of combinato- rial problems that can be solved via submodular maximization (either directly on the objective function or via submodular surrogates). We introduce a data-driven optimization framework based on the submodular-norm loss, a novel loss func- tion that encourages the resulting objective to exhibit diminishing returns. Our framework outputs a surrogate objective that is efficient to train, approximately submodular, and can be made permutation-invariant. The latter two properties al- low us to prove strong approximation guarantees for the learned greedy heuristic. Furthermore, our model is easily integrated with modern deep imitation learning pipelines for sequential prediction tasks. We demonstrate the performance of our algorithm on a variety of batched and sequential optimization tasks, including set cover, active learning, and data-driven protein engineering. 

   more » « less
4. FabricFlowNet: Bimanual Cloth Manipulation with a Flow-based Policy

   Weng, Thomas; Bajracharya, Sujay; Wang, Yufei; Agrawal, Khush; Held, David (January 2021, Conference on Robot Learning)

   We address the problem of goal-directed cloth manipulation, a chal- lenging task due to the deformability of cloth. Our insight is that optical flow, a technique normally used for motion estimation in video, can also provide an effective representation for corresponding cloth poses across observation and goal images. We introduce FabricFlowNet (FFN), a cloth manipulation policy that leverages flow as both an input and as an action representation to improve performance. FabricFlowNet also elegantly switches between dual-arm and single- arm actions based on the desired goal. We show that FabricFlowNet significantly outperforms state-of-the-art model-free and model-based cloth manipulation policies. We also present real-world experiments on a bimanual system, demonstrating effective sim-to-real transfer. Finally, we show that our method generalizes when trained on a single square cloth to other cloth shapes, such as T-shirts and rectangular cloths. Video and other supplementary materials are available at: https://sites.google.com/view/fabricflownet. 

   more » « less
5. Model-Centered Assurance for Autonomous Systems

   https://doi.org/10.1007/978-3-030-54549-9_15  

   Jha, Susmit; Rushby, John; Natarajan, Shankar (October 2020, 39th International Conference on Computer Safety, Reliability and Security (SafeComp), 2020)

   The functions of an autonomous system can generally be partitioned into those concerned with perception and those concerned with action. Perception builds and maintains an internal model of the world (i.e., the system's environment) that is used to plan and execute actions to accomplish a goal established by human supervisors. Accordingly, assurance decomposes into two parts: a) ensuring that the model is an accurate representation of the world as it changes through time and b) ensuring that the actions are safe (and eective), given the model. Both perception and action may employ AI, including machine learning (ML), and these present challenges to assurance. However, it is usually feasible to guard the actions with traditionally engineered and assured monitors, and thereby ensure safety, given the model. Thus, the model becomes the central focus for assurance. We propose an architecture and methods to ensure the accuracy of models derived from sensors whose interpretation uses AI and ML. Rather than derive the model from sensors bottom-up, we reverse the process and use the model to predict sensor interpretation. Small prediction errors indicate the world is evolving as expected and the model is updated accordingly. Large prediction errors indicate surprise, which may be due to errors in sensing or interpretation, or unexpected changes in the world (e.g., a pedestrian steps into the road). The former initiate error masking or recovery, while the latter requires revision to the model. Higher-level AI functions assist in diagnosis and execution of these tasks. Although this two-level architecture where the lower level does \predictive processing" and the upper performs more re ective tasks, both focused on maintenance of a world model, is derived by engineering considerations, it also matches a widely accepted theory of human cognition. 

   more » « less