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.
The spatial correlations and the temporal contexts are indispensable in Electroencephalogram (EEG)-based emotion recognition. However, the learning of complex spatial correlations among several channels is a challenging problem. Besides, the temporal contexts learning is beneficial to emphasize the critical EEG frames because the subjects only reach the prospective emotion during part of stimuli. Hence, we propose a novel Spatial-Temporal Information Learning Network (STILN) to extract the discriminative features by capturing the spatial correlations and temporal contexts. Specifically, the generated 2D power topographic maps capture the dependencies among electrodes, and they are fed to the CNN-based spatial feature extraction network. Furthermore, Convolutional Block Attention Module (CBAM) recalibrates the weights of power topographic maps to emphasize the crucial brain regions and frequency bands. Meanwhile, Batch Normalizations (BNs) and Instance Normalizations (INs) are appropriately combined to relieve the individual differences. In the temporal contexts learning, we adopt the Bidirectional Long Short-Term Memory Network (Bi-LSTM) network to capture the dependencies among the EEG frames. To validate the effectiveness of the proposed method, subject-independent experiments are conducted on the public DEAP dataset. The proposed method has achieved the outstanding performance, and the accuracies of arousal and valence classification have reached 0.6831 and 0.6752 respectively.
Although data-driven motion mapping methods are promising to allow intuitive robot control and teleoperation that generate human-like robot movement, they normally require tedious pair-wise training for each specific human and robot pair. This paper proposes a transferability-based mapping scheme to allow new robot and human input systems to leverage the mapping of existing trained pairs to form a mapping transfer chain, which will reduce the number of new pair-specific mappings that need to be generated. The first part of the mapping schematic is the development of a Synergy Mapping via Dual-Autoencoder (SyDa) method. This method uses the latent features from two autoencoders to extract the common synergy of the two agents. Secondly, a transferability metric is created that approximates how well the mapping between a pair of agents will perform compared to another pair before creating the motion mapping models. Thus, it can guide the formation of an optimal mapping chain for the new human-robot pair. Experiments with human subjects and a Pepper robot demonstrated 1) The SyDa method improves the accuracy and generalizability of the pair mappings, 2) the SyDa method allows for bidirectional mapping that does not prioritize the direction of mapping motion, and 3) the transferability metric measures how compatible two agents are for accurate teleoperation. The combination of the SyDa method and transferability metric creates generalizable and accurate mapping need to create the transfer mapping chain.
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.
Autonomous grasping is challenging due to the high computational cost caused by multi-fingered robotic hands and their interactions with objects. Various analytical methods have been developed yet their high computational cost limits the adoption in real-world applications. Learning-based grasping can afford real-time motion planning thanks to its high computational efficiency. However, it needs to explore large search spaces during its learning process. The search space causes low learning efficiency, which has been the main barrier to its practical adoption. In this work, we develop a novel Physics-Guided Deep Reinforcement Learning with a Hierarchical Reward Mechanism, which combines the benefits of both analytical methods and learning-based methods for autonomous grasping. Different from 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 learning outcomes. Further, a hierarchical reward mechanism is developed to enable the robot to learn the grasping task in a prioritized way. It is validated in a grasping task with a MICO robot arm in simulation and physical experiments. The results show that our method outperformed the baseline in task performance by 48% and learning efficiency by 40%.
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.
Modern CNN-based face detectors have achieved tremendous strides due to large annotated datasets. However, misaligned results with high detection confidence but low localization accuracy restrict the further improvement of detection performance. In this paper, we first generate detection results on training set itself. Surprisingly, a considerable part of them exist the same misalignment problem. Then, we carefully examine these misaligned cases and point out annotation inconsistency is the main reason. Finally, we propose a novel Bounding-Box Deep Calibration (BDC) method to reasonably replace inconsistent annotations with model predicted bounding-boxes and create a new annotation file for training set. Extensive experiments on WIDER FACE dataset show the effectiveness of BDC on improving models' precision and recall rate. Our simple and effective method provides a new direction for improving face detection. Source code is available at https://github.com/shiluo1990/BDC.
Wire-feed laser additive manufacturing (WLAM) is gaining wide interest due to its high level of automation, high deposition rates, and good quality of printed parts. In-process monitoring and feedback controls that would reduce the uncertainty in the quality of the material are in the early stages of development. Machine learning promises the ability to accelerate the adoption of new processes and property design in additive manufacturing by making process-structure-property connections between process setting inputs and material quality outcomes. The molten pool dimensional information and temperature are the indicators for achieving the high quality of the build, which can be directly controlled by processing parameters. For the purpose of in situ quality control, the process parameters should be controlled in real-time based on sensed information from the process, in particular the molten pool. Thus, the molten pool-process relations are of preliminary importance. This paper analyzes experimentally collected in situ sensing data from the molten pool under a set of controlled process parameters in a WLAM system. The variations in the steady-state and transient state of the molten pool are presented with respect to the change of independent process parameters. A multi-modality convolutional neural network (CNN) architecture is proposed for predicting the control parameter directly from the measurable molten pool sensor data for achieving desired geometric and microstructural properties. Dropout and regularization are applied to the CNN architecture to avoid the problem of overfitting. The results highlighted that the multi-modal CNN, which receives temperature profile as an external feature to the features extracted from the image data, has improved prediction performance compared to the image-based uni-modality CNN approach.