Search

Simulation to Real-World Transfer allows affordable and fast training of learning-based robots for manipulation tasks using Deep Reinforcement Learning methods. Currently, Sim2Real uses Asymmetric Actor-Critic approaches to reduce the rich idealized features in simulation to the accessible ones in the real world. However, the feature reduction from the simulation to the real world is conducted through an empirically defined one-step curtail. Small feature reduction does not sufficiently remove the actor's features, which may still cause difficulty setting up the physical system, while large feature reduction may cause difficulty and inefficiency in training. To address this issue, we proposed Curriculum-based Sensing Reduction to enable the actor to start with the same rich feature space as the critic and then get rid of the hard-to-extract features step-by-step for higher training performance and better adaptation for real-world feature space. The reduced features are replaced with random signals from a Deep Random Generator to remove the dependency between the output and the removed features and avoid creating new dependencies. The methods are evaluated on the Allegro robot hand in a real-world in-hand manipulation task. The results show that our methods have faster training and higher task performance than baselines and can solve real-world tasks when selected tactile features are reduced.

Deep Reinforcement Learning has shown its capability to solve the high degrees of freedom in control and the complex interaction with the object in the multi-finger dexterous in-hand manipulation tasks. Current DRL approaches prefer sparse rewards to dense rewards for the ease of training but lack behavior constraints during the manipulation process, leading to aggressive and unstable policies that are insufficient for safety-critical in-hand manipulation tasks. Dense rewards can regulate the policy to learn stable manipulation behaviors with continuous reward constraints but are hard to empirically define and slow to converge optimally. This work proposes the Finger-specific Multi-agent Shadow Reward (FMSR) method to determine the stable manipulation constraints in the form of dense reward based on the state-action occupancy measure, a general utility of DRL that is approximated during the learning process. Information Sharing (IS) across neighboring agents enables consensus training to accelerate the convergence. The methods are evaluated in two in-hand manipulation tasks on the Shadow Hand. The results show FMSR+IS converges faster in training, achieving a higher task success rate and better manipulation stability than conventional dense reward. The comparison indicates FMSR+IS achieves a comparable success rate even with the behavior constraint but much better manipulation stability than the policy trained with a sparse reward.

Deep learning appearance-based 3D gaze estimation is gaining popularity due to its minimal hardware requirements and being free of constraint. Unreliable and overconfident inferences, however, still limit the adoption of this gaze estimation method. To address the unreliable and overconfident issues, we introduce a confidence-aware model that predicts uncertainties together with gaze angle estimations. We also introduce a novel effectiveness evaluation method based on the causality between eye feature degradation and the rise in inference uncertainty to assess the uncertainty estimation. Our confidence-aware model demonstrates reliable uncertainty estimations while providing angular estimation accuracies on par with the state-of-the-art. Compared with the existing statistical uncertainty-angular-error evaluation metric, the proposed effectiveness evaluation approach can more effectively judge inferred uncertainties' performance at each prediction., Comment: 9 pages 12 figures

In-hand manipulation is challenging for a multi-finger robotic hand due to its high degrees of freedom and the complex interaction with the object. To enable in-hand manipulation, existing deep reinforcement learning based approaches mainly focus on training a single robot-structure-specific policy through the centralized learning mechanism, lacking adaptability to changes like robot malfunction. To solve this limitation, this work treats each finger as an individual agent and trains multiple agents to control their assigned fingers to complete the in-hand manipulation task cooperatively. We propose the Multi-Agent Global-Observation Critic and Local-Observation Actor (MAGCLA) method, where the critic can observe all agents' actions globally, and the actor only locally observes its neighbors' actions. Besides, conventional individual experience replay may cause unstable cooperation due to the asynchronous performance increment of each agent, which is critical for in-hand manipulation tasks. To solve this issue, we propose the Synchronized Hindsight Experience Replay (SHER) method to synchronize and efficiently reuse the replayed experience across all agents. The methods are evaluated in two in-hand manipulation tasks on the Shadow dexterous hand. The results show that SHER helps MAGCLA achieve comparable learning efficiency to a single policy, and the MAGCLA approach is more generalizable in different tasks. The trained policies have higher adaptability in the robot malfunction test compared to the baseline multi-agent and single-agent approaches., Comment: Submitted to ICRA 2023

Learning-based grasping can afford real-time grasp motion planning of multi-fingered robotics hands thanks to its high computational efficiency. However, learning-based methods are required to explore large search spaces during the learning process. The search space causes low learning efficiency, which has been the main barrier to its practical adoption. In addition, the trained policy lacks a generalizable outcome unless objects are identical to the trained objects. In this work, we develop a novel Physics-Guided Deep Reinforcement Learning with a Hierarchical Reward Mechanism to improve learning efficiency and generalizability for learning-based autonomous grasping. Unlike conventional observation-based grasp learning, physics-informed metrics are utilized to convey correlations between features associated with hand structures and objects to improve learning efficiency and outcomes. Further, the hierarchical reward mechanism enables the robot to learn prioritized components of the grasping tasks. Our method is validated in robotic grasping tasks with a 3-finger MICO robot arm. The results show that our method outperformed the standard Deep Reinforcement Learning methods in various robotic grasping tasks.

Dexterous manipulation tasks usually have multiple objectives, and the priorities of these objectives may vary at different phases of a manipulation task. Varying priority makes a robot hardly or even failed to learn an optimal policy with a deep reinforcement learning (DRL) method. To solve this problem, we develop a novel Adaptive Hierarchical Reward Mechanism (AHRM) to guide the DRL agent to learn manipulation tasks with multiple prioritized objectives. The AHRM can determine the objective priorities during the learning process and update the reward hierarchy to adapt to the changing objective priorities at different phases. The proposed method is validated in a multi-objective manipulation task with a JACO robot arm in which the robot needs to manipulate a target with obstacles surrounded. The simulation and physical experiment results show that the proposed method improved robot learning in task performance and learning efficiency., Comment: Accepted by the Journal of Intelligent & Robotic Systems

In human-robot cooperation, the robot cooperates with humans to accomplish the task together. Existing approaches assume the human has a specific goal during the cooperation, and the robot infers and acts toward it. However, in real-world environments, a human usually only has a general goal (e.g., general direction or area in motion planning) at the beginning of the cooperation, which needs to be clarified to a specific goal (i.e., an exact position) during cooperation. The specification process is interactive and dynamic, which depends on the environment and the partner's behavior. The robot that does not consider the goal specification process may cause frustration to the human partner, elongate the time to come to an agreement, and compromise team performance. This work presents the Evolutionary Value Learning approach to model the dynamics of the goal specification process with State-based Multivariate Bayesian Inference and goal specificity-related features. This model enables the robot to enhance the process of the human's goal specification actively and find a cooperative policy in a Deep Reinforcement Learning manner. Our method outperforms existing methods with faster goal specification processes and better team performance in a dynamic ball balancing task with real human subjects., Comment: Published on RAL

Recent advances in supervised learning and reinforcement learning have provided new opportunities to apply related methodologies to automated driving. However, there are still challenges to achieve automated driving maneuvers in dynamically changing environments. Supervised learning algorithms such as imitation learning can generalize to new environments by training on a large amount of labeled data, however, it can be often impractical or cost-prohibitive to obtain sufficient data for each new environment. Although reinforcement learning methods can mitigate this data-dependency issue by training the agent in a trial-and-error way, they still need to re-train policies from scratch when adapting to new environments. In this paper, we thus propose a meta reinforcement learning (MRL) method to improve the agent's generalization capabilities to make automated lane-changing maneuvers at different traffic environments, which are formulated as different traffic congestion levels. Specifically, we train the model at light to moderate traffic densities and test it at a new heavy traffic density condition. We use both collision rate and success rate to quantify the safety and effectiveness of the proposed model. A benchmark model is developed based on a pretraining method, which uses the same network structure and training tasks as our proposed model for fair comparison. The simulation results shows that the proposed method achieves an overall success rate up to 20% higher than the benchmark model when it is generalized to the new environment of heavy traffic density. The collision rate is also reduced by up to 18% than the benchmark model. Finally, the proposed model shows more stable and efficient generalization capabilities adapting to the new environment, and it can achieve 100% successful rate and 0% collision rate with only a few steps of gradient updates., Comment: 8 pages, 6 figures

Shared control in teleoperation for providing robot assistance to accomplish object manipulation, called telemanipulation, is a new promising yet challenging problem. This has unique challenges--on top of teleoperation challenges in general--due to difficulties of physical discrepancy between human hands and robot hands as well as the fine motion constraints to constitute task success. We present an intuitive shared-control strategy where the focus is on generating robotic grasp poses which are better suited for human perception of successful teleoperated object manipulation and feeling of being in control of the robot, rather than developing objective stable grasp configurations for task success or following the human motion. The former is achieved by understanding human intent and autonomously taking over control on that inference. The latter is achieved by considering human inputs as hard motion constraints which the robot must abide. An arbitration of these two enables a trade-off for the subsequent robot motion to balance accomplishing the inferred task and motion constraints imposed by the operator. The arbitration framework adapts to the level of physical discrepancy between the human and different robot structures, enabling the assistance to indicate and appear to intuitively follow the user. To understand how users perceive good arbitration in object telemanipulation, we have conducted a user study with a hands-free telemanipulation setup to analyze the effect of factors including task predictability, perceived following, and user preference. The hands-free telemanipulation scene is chosen as the validation platform due to its more urgent need of intuitive robotics assistance for task success.

Enabling robots to provide effective assistance yet still accommodating the operator's commands for telemanipulation of an object is very challenging because robot's assistive action is not always intuitive for human operators and human behaviors and preferences are sometimes ambiguous for the robot to interpret. Although various assistance approaches are being developed to improve the control quality from different optimization perspectives, the problem still remains in determining the appropriate approach that satisfies the fine motion constraints for the telemanipulation task and preference of the operator. To address these problems, we developed a novel preference-aware assistance knowledge learning approach. An assistance preference model learns what assistance is preferred by a human, and a stagewise model updating method ensures the learning stability while dealing with the ambiguity of human preference data. Such a preference-aware assistance knowledge enables a teleoperated robot hand to provide more active yet preferred assistance toward manipulation success. We also developed knowledge transfer methods to transfer the preference knowledge across different robot hand structures to avoid extensive robot-specific training. Experiments to telemanipulate a 3-finger hand and 2-finger hand, respectively, to use, move, and hand over a cup have been conducted. Results demonstrated that the methods enabled the robots to effectively learn the preference knowledge and allowed knowledge transfer between robots with less training effort.

Applying Deep Reinforcement Learning (DRL) to Human-Robot Cooperation (HRC) in dynamic control problems is promising yet challenging as the robot needs to learn the dynamics of the controlled system and dynamics of the human partner. In existing research, the robot powered by DRL adopts coupled observation of the environment and the human partner to learn both dynamics simultaneously. However, such a learning strategy is limited in terms of learning efficiency and team performance. This work proposes a novel task decomposition method with a hierarchical reward mechanism that enables the robot to learn the hierarchical dynamic control task separately from learning the human partner's behavior. The method is validated with a hierarchical control task in a simulated environment with human subject experiments. Our method also provides insight into the design of the learning strategy for HRC. The results show that the robot should learn the task first to achieve higher team performance and learn the human first to achieve higher learning efficiency., Comment: Accepted by SMC2021

Lane-change maneuvers are commonly executed by drivers to follow a certain routing plan, overtake a slower vehicle, adapt to a merging lane ahead, etc. However, improper lane change behaviors can be a major cause of traffic flow disruptions and even crashes. While many rule-based methods have been proposed to solve lane change problems for autonomous driving, they tend to exhibit limited performance due to the uncertainty and complexity of the driving environment. Machine learning-based methods offer an alternative approach, as Deep reinforcement learning (DRL) has shown promising success in many application domains including robotic manipulation, navigation, and playing video games. However, applying DRL to autonomous driving still faces many practical challenges in terms of slow learning rates, sample inefficiency, and safety concerns. In this study, we propose an automated lane change strategy using proximal policy optimization-based deep reinforcement learning, which shows great advantages in learning efficiency while still maintaining stable performance. The trained agent is able to learn a smooth, safe, and efficient driving policy to make lane-change decisions (i.e. when and how) in a challenging situation such as dense traffic scenarios. The effectiveness of the proposed policy is validated by using metrics of task success rate and collision rate. The simulation results demonstrate the lane change maneuvers can be efficiently learned and executed in a safe, smooth, and efficient manner.

Stabilization and trajectory control of a quadrotor carrying a suspended load with a fixed known mass has been extensively studied in recent years. However, the load mass is not always known beforehand or may vary during the practical transportations. This mass uncertainty brings uncertain disturbances to the quadrotor system, causing existing controllers to have worse stability and trajectory tracking performance. To improve the quadrotor stability and trajectory tracking capability in this situation, we fully investigate the impacts of the uncertain load mass on the quadrotor. By comparing the performances of three different controllers -- the proportional-derivative (PD) controller, the sliding mode controller (SMC), and the model predictive controller (MPC) -- stabilization rather than trajectory tracking error is proved to be the main influence in the load mass uncertainty. A critical motion mass exists for the quadrotor to maintain a desired transportation performance. Moreover, simulation results verify that a controller with strong robustness against disturbances is a good choice for practical applications., Comment: 56 pages, 12 figures, article submitted to ASME Journal of Dynamic Systems Measurement and Control, 2016 April