Point clouds are a widely available and canonical data modality which conveys the 3D geometry of a scene. Despite significant progress in classification and segmentation from point clouds, policy learning from such a modality remains challenging, and most prior works in imitation learning focus on learning policies from images or state information. In this paper, we propose a novel framework for learning policies from point clouds for robotic manipulation with tools. We use a novel neural network, ToolFlowNet, which predicts dense per-point flow on the tool that the robot controls, and then uses the flow to derive the transformation that the robot should execute. We apply this framework to imitation learning of challenging deformable object manipulation tasks with continuous movement of tools, including scooping and pouring, and demonstrate significantly improved performance over baselines which do not use flow. We perform physical scooping experiments with ToolFlowNet and find that we can attain 78% scooping success.

@inproceedings{Seita2022toolflownet,
    title={ToolFlowNet: Robotic Manipulation with Tools via Predicting Tool Flow from Point Clouds},
    author={Seita, Daniel and Wang, Yufei and Shetty, Sarthak, and Li Edward, and Erickson, Zackory and Held, David},
    booktitle={Conference on Robot Learning},
    year={2022}}       
                                    

Robotic manipulation of highly deformable cloth presents a promising opportunity to assist people with several daily tasks, such as washing dishes; folding laundry; or dressing, bathing, and hygiene assistance for individuals with severe motor impairments. In this work, we introduce a formulation that enables a collaborative robot to perform visual haptic reasoning with cloth -- the act of inferring the location and magnitude of applied forces during physical interaction. We present two distinct model representations, trained in physics simulation, that enable haptic reasoning using only visual and robot kinematic observations. We conducted quantitative evaluations of these models in simulation for robot-assisted dressing, bathing, and dish washing tasks, and demonstrate that the trained models can generalize across different tasks with varying interactions, human body sizes, and object shapes. We also present results with a real-world mobile manipulator, which used our simulation-trained models to estimate applied contact forces while performing physically assistive tasks with cloth.

@article{wang2022visual,
    title={Visual Haptic Reasoning: Estimating Contact Forces by Observing Deformable Object Interactions},
    author={Wang, Yufei and Held, David and Erickson, Zackory},
    journal={IEEE Robotics and Automation Letters},
    volume={7},
    number={4},
    pages={11426--11433},
    year={2022},
    publisher={IEEE}
    }           
                                    

Robotic manipulation of cloth remains challenging due to the complex dynamics of cloth, lack of a low-dimensional state representation, and self-occlusions. In contrast to previous model-based approaches that learn a pixel-based dynamics model or a compressed latent vector dynamics, we propose to learn a particle-based dynamics model from a partial point cloud observation. To overcome the challenges of partial observability, we infer which visible points are connected on the underlying cloth mesh. We then learn a dynamics model over this visible connectivity graph. Compared to previous learning-based approaches, our model poses strong inductive bias with its particle based representation for learning the underlying cloth physics; it can generalize to cloths with novel shapes; it is invariant to visual features; and the predictions can be more easily visualized. We show that our method greatly outperforms previous state-of-the-art model-based and model-free reinforcement learning methods in simulation. Furthermore, we demonstrate zero-shot sim-to-real transfer where we deploy the model trained in simulation on a Franka arm and show that the model can successfully smooth cloths of different materials, geometries and colors from crumpled configurations. Videos can be found in the supplement and on our anonymous project website: https://sites.google.com/view/vcd-cloth.

                                @inproceedings{lin2021VCD,
                                    title={Learning Visible Connectivity Dynamics for Cloth Smoothing},
                                    author={Lin, Xingyu and Wang, Yufei and Huang, Zixuan and Held, David},
                                    booktitle={Conference on Robot Learning},
                                    year={2021}}
                            

We address the problem of goal-directed cloth manipulation, a challenging 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.

                                        @inproceedings{weng2021fabricflownet,
                                            title={FabricFlowNet: Bimanual Cloth Manipulation 
                                               with a Flow-based Policy},
                                            author={Weng, Thomas and Bajracharya, Sujay and 
                                               Wang, Yufei and Agrawal, Khush and Held, David},
                                            booktitle={Conference on Robot Learning},
                                            year={2021}
                                           }
                                    

Current image-based reinforcement learning (RL) algorithms typically operate on the whole image without performing object-level reasoning. This leads to inefficient goal sampling and ineffective reward functions. In this paper, we improve upon previous visual self-supervised RL by incorporating object-level reasoning and occlusion reasoning. Specifically, we use unknown object segmentation to ignore distractors in the scene for better reward computation and goal generation; we further enable occlusion reasoning by employing a novel auxiliary loss and training scheme. We demonstrate that our proposed algorithm, ROLL (Reinforcement learning with Object Level Learning), learns dramatically faster and achieves better final performance compared with previous methods in several simulated visual control tasks. Project video and code are available at https://sites.google.com/andrew.cmu.edu/roll.

    @inproceedings{corl2020roll,
        title={ROLL: Visual Self-Supervised Reinforcement Learning with Object Reasoning},
        author={Wang, Yufei and Narasimhan Gautham and Lin, Xingyu and Okorn, Brian and Held, David},
        booktitle={Conference on Robot Learning},
        year={2020}
    }
                            

Manipulating deformable objects has long been a challenge in robotics due to its high dimensional state representation and complex dynamics. Recent success in deep reinforcement learning provides a promising direction for learning to manipulate deformable objects with data driven methods. However, existing reinforcement learning benchmarks only cover tasks with direct state observability and simple low-dimensional dynamics or with relatively simple image-based environments, such as those with rigid objects. In this paper, we present SoftGym, a set of open-source simulated benchmarks for manipulating deformable objects, with a standard OpenAI Gym API and a Python interface for creating new environments. Our benchmark will enable reproducible research in this important area. Further, we evaluate a variety of algorithms on these tasks and highlight challenges for reinforcement learning algorithms, including dealing with a state representation that has a high intrinsic dimensionality and is partially observable. The experiments and analysis indicate the strengths and limitations of existing methods in the context of deformable object manipulation that can help point the way forward for future methods development. Code and videos of the learned policies can be found on our project website.

    @inproceedings{corl2020softgym,
        title={SoftGym: Benchmarking Deep Reinforcement Learning for Deformable Object Manipulation},
        author={Lin, Xingyu and Wang, Yufei and Olkin, Jake and Held, David},
        booktitle={Conference on Robot Learning},
        year={2020}
    }
                            

Imitation learning is well-suited for robotic tasks where it is difficult to directly program the behavior or specify a cost for optimal control. In this work, we propose a method for learning the reward function (and the corresponding policy) to match the expert state density. Our main result is the analytic gradient of any f-divergence between the agent and expert state distribution w.r.t. reward parameters. Based on the derived gradient, we present an algorithm, f-IRL, that recovers a stationary reward function from the expert density by gradient descent. We show that f-IRL can learn behaviors from a hand-designed target state density or implicitly through expert observations. Our method outperforms adversarial imitation learning methods in terms of sample efficiency and the required number of expert trajectories on IRL benchmarks. Moreover, we show that the recovered reward function can be used to quickly solve downstream tasks, and empirically demonstrate its utility on hard-to-explore tasks and for behavior transfer across changes in dynamics.

    @inproceedings{firl2020corl,
        title={f-IRL: Inverse Reinforcement Learning via State Marginal Matching},
        author={Ni, Tianwei and Sikchi, Harshit and Wang, Yufei and Gupta, Tejus and Lee, Lisa and Eysenbach, Ben},
        booktitle={Conference on Robot Learning},
        year={2020}
    }
                            

Exploration-exploitation dilemma has long been a crucial issue in reinforcement learning. In this paper, we propose a new approach to automatically balance between these two. Our method is built upon the Soft Actor-Critic (SAC) algorithm, which uses an "entropy temperature" that balances the original task reward and the policy entropy, and hence controls the trade-off between exploitation and exploration. It is empirically shown that SAC is very sensitive to this hyperparameter, and the follow-up work (SAC-v2), which uses constrained optimization for automatic adjustment, has some limitations. The core of our method, namely Meta-SAC, is to use metagradient along with a novel meta objective to automatically tune the entropy temperature in SAC. We show that Meta-SAC achieves promising performances on several of the Mujoco benchmarking tasks, and outperforms SAC-v2 over 10% in one of the most challenging tasks, humanoid-v2.

In reinforcement learning, Return, which is the weighted accumulated future rewards, and Value, which is the expected return, serve as the objective that guides the learning of the policy. In classic RL, return is defined as the exponentially discounted sum of future rewards. One key insight is that there could be many feasible ways to define the form of the return function (and thus the value), from which the same optimal policy can be derived, yet these different forms might render dramatically different speeds of learning this policy. In this paper, we research how to modify the form of the return function to enhance the learning towards the optimal policy. We propose to use a general mathematical form for return function, and employ meta-learning to learn the optimal return function in an end-to-end manner. We test our methods on a specially designed maze environment and several Atari games, and our experimental results clearly indicate the advantages of automatically learning optimal return functions in reinforcement learning.

Conservation laws are considered to be fundamental laws of nature. It has broad applications in many fields, including physics, chemistry, biology, geology, and engineering. Solving the differential equations associated with conservation laws is a major branch in computational mathematics. The recent success of machine learning, especially deep learning in areas such as computer vision and natural language processing, has attracted a lot of attention from the community of computational mathematics and inspired many intriguing works in combining machine learning with traditional methods. In this paper, we are the first to view numerical PDE solvers as an MDP and to use (deep) RL to learn new solvers. As proof of concept, we focus on 1-dimensional scalar conservation laws. We deploy the machinery of deep reinforcement learning to train a policy network that can decide on how the numerical solutions should be approximated in a sequential and spatial-temporal adaptive manner. We will show that the problem of solving conservation laws can be naturally viewed as a sequential decision-making process, and the numerical schemes learned in such a way can easily enforce long-term accuracy. Furthermore, the learned policy network is carefully designed to determine a good local discrete approximation based on the current state of the solution, which essentially makes the proposed method a meta-learning approach. In other words, the proposed method is capable of learning how to discretize for a given situation mimicking human experts. Finally, we will provide details on how the policy network is trained, how well it performs compared with some state-of-the-art numerical solvers such as WENO schemes, and supervised learning based approach L3D and PINN, and how well it generalizes.

Green Security Games (GSGs) have been proposed and applied to optimize patrols conducted by law enforcement agencies in green security domains such as combating poaching, illegal logging and overfishing. However, real-time information such as footprints and agents' subsequent actions upon receiving the information, e.g., rangers following the footprints to chase the poacher, have been neglected in previous work. To fill the gap, we first propose a new game model GSG-I which augments GSGs with sequential movement and the vital element of real-time information. Second, we design a novel deep reinforcement learning-based algorithm, DeDOL, to compute a patrolling strategy that adapts to the real-time information against a best-responding attacker. DeDOL is built upon the double oracle framework and the policy-space response oracle, solving a restricted game and iteratively adding best response strategies to it through training deep Q-networks. Exploring the game structure, DeDOL uses domain-specific heuristic strategies as initial strategies and constructs several local modes for efficient and parallelized training. To our knowledge, this is the first attempt to use Deep Q-Learning for security games.

    @inproceedings{wang2019deep,
        title={Deep reinforcement learning for green security games with real-time information},
        author={Wang, Yufei and Shi, Zheyuan Ryan and Yu, Lantao and Wu, Yi and Singh, Rohit and Joppa, Lucas and Fang, Fei},
        booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
        volume={33},
        number={01},
        pages={1401--1408},
        year={2019}
    }