More Like this

1. Learning Task-Driven Control Policies via Information Bottlenecks

   https://doi.org/10.15607/RSS.2020.XVI.101  

   Pacelli, Vincent; Majumdar, Anirudha (July 2020, Robotics: Science and Systems (RSS))

   null (Ed.)

   This paper presents a reinforcement learning approach to synthesizing task-driven control policies for robotic systems equipped with rich sensory modalities (e.g., vision or depth). Standard reinforcement learning algorithms typically produce policies that tightly couple control actions to the entirety of the system's state and rich sensor observations. As a consequence, the resulting policies can often be sensitive to changes in task-irrelevant portions of the state or observations (e.g., changing background colors). In contrast, the approach we present here learns to create a task-driven representation that is used to compute control actions. Formally, this is achieved by deriving a policy gradient-style algorithm that creates an information bottleneck between the states and the task-driven representation; this constrains actions to only depend on task-relevant information. We demonstrate our approach in a thorough set of simulation results on multiple examples including a grasping task that utilizes depth images and a ball-catching task that utilizes RGB images. Comparisons with a standard policy gradient approach demonstrate that the task-driven policies produced by our algorithm are often significantly more robust to sensor noise and task-irrelevant changes in the environment. 

   more » « less
2. Learning Rope Manipulation Policies Using Dense Object Descriptors Trained on Synthetic Depth Data

   https://doi.org/10.1109/ICRA40945.2020.9197121  

   Sundaresan, Priya; Grannen, Jennifer; Thananjeyan, Brijen; Balakrishna, Ashwin; Laskey, Michael; Stone, Kevin; Gonzalez, Joseph E.; Goldberg, Ken (May 2020, 2020 IEEE International Conference on Robotics and Automation (ICRA))

   null (Ed.)

   Robotic manipulation of deformable 1D objects such as ropes, cables, and hoses is challenging due to the lack of high-fidelity analytic models and large configuration spaces. Furthermore, learning end-to-end manipulation policies directly from images and physical interaction requires significant time on a robot and can fail to generalize across tasks. We address these challenges using interpretable deep visual representations for rope, extending recent work on dense object descriptors for robot manipulation. This facilitates the design of interpretable and transferable geometric policies built on top of the learned representations, decoupling visual reasoning and control. We present an approach that learns point-pair correspondences between initial and goal rope configurations, which implicitly encodes geometric structure, entirely in simulation from synthetic depth images. We demonstrate that the learned representation - dense depth object descriptors (DDODs) - can be used to manipulate a real rope into a variety of different arrangements either by learning from demonstrations or using interpretable geometric policies. In 50 trials of a knot-tying task with the ABB YuMi Robot, the system achieves a 66% knot-tying success rate from previously unseen configurations. See https://tinyurl.com/rope-learning for supplementary material and videos. 

   more » « less
3. Learning Interpretable Policies in Hindsight-Observable POMDPs through Partially Supervised Reinforcement Learning

   Lanier, Michael; Xu, Ying; Vorobeychik, Yevgeniy; Jacobs, Nathan; Zhang, Chongjie (December 2024, International Conference on Machine Learning and Applications)

   Deep reinforcement learning has demonstrated re- markable achievements across diverse domains such as video games, robotic control, autonomous driving, and drug discovery. Common methodologies in partially observable domains largely lean on end-to-end learning from high-dimensional observations, such as images, without explicitly reasoning about true state. We suggest an alternative direction, introducing the Partially Supervised Reinforcement Learning (PSRL) framework. At the heart of PSRL is the fusion of both supervised and unsupervised learning. The approach leverages a state estimator to distill supervised semantic state information from high-dimensional observations which are often fully observable at training time. This yields more interpretable policies that compose state predictions with control. In parallel, it captures an unsupervised latent representation. These two—the semantic state and the latent state—are then fused and utilized as inputs to a policy network. This juxtaposition offers practitioners a flexible and dynamic spectrum: from emphasizing supervised state information to integrating richer, latent insights. Extensive experimental results indicate that by merging these dual representations, PSRL offers a balance, enhancing interpretability while preserving, and often significantly outperforming, the performance benchmarks set by traditional methods in terms of reward and convergence speed. 

   more » « less
4. Can Direct Latent Model Learning Solve Linear Quadratic Gaussian Control?

   Tian, Yi; Zhang, Kaiqing; Tedrake, Russ; Sra, Suvrit (January 2023, Conference on Learning for Dynamics and Control)

   We study the task of learning state representations from potentially high-dimensional observations, with the goal of controlling an unknown partially observable system. We pursue a direct latent model learning approach, where a dynamic model in some latent state space is learned by predicting quantities directly related to planning (e.g., costs) without reconstructing the observations. In particular, we focus on an intuitive cost-driven state representation learning method for solving Linear Quadratic Gaussian (LQG) control, one of the most fundamental partially observable control problems. As our main results, we establish finite-sample guarantees of finding a near-optimal state representation function and a near-optimal controller using the directly learned latent model. To the best of our knowledge, despite various empirical successes, prior to this work it was unclear if such a cost-driven latent model learner enjoys finite-sample guarantees. Our work underscores the value of predicting multi-step costs, an idea that is key to our theory, and notably also an idea that is known to be empirically valuable for learning state representations. 

   more » « less
5. Local Koopman Operators for Data-Driven Control of Robotic Systems

   https://doi.org/10.15607/RSS.2019.XV.054  

   Mamakoukas, Giorgos; Castano, Maria; Tan, Xiaobo; Murphey, Todd (June 2019, Robotics: science and systems)

   This paper presents a data-driven methodology for linear embedding of nonlinear systems. Utilizing structural knowledge of general nonlinear dynamics, the authors exploit the Koopman operator to develop a systematic, data-driven approach for constructing a linear representation in terms of higher order derivatives of the underlying nonlinear dynamics. With the linear representation, the nonlinear system is then controlled with an LQR feedback policy, the gains of which need to be calculated only once. As a result, the approach enables fast control synthesis. We demonstrate the efficacy of the approach with simulations and experimental results on the modeling and control of a tail-actuated robotic fish and show that the proposed policy is comparable to backstepping control. To the best of our knowledge, this is the first experimental validation of Koopman-based LQR control. 

   more » « less