This work focuses on the problem of in-hand manipulation and regrasping of objects with parallel grippers. We propose Dexterous Manipulation Graph (DMG) as a representation on which we define planning for in-hand manipulation and regrasping. The DMG is a disconnected undirected graph that represents the possible motions of a finger along the object's surface. We formulate the in-hand manipulation and regrasping problem as a graph search problem from the initial to the final configuration. The resulting plan is a sequence of coordinated in-hand pushing and regrasping movements. We propose a dual-arm system for the execution of the sequence where both hands are used interchangeably. We demonstrate our approach on an ABB Yumi robot tasked with different grasp reconfigurations.
Modelling of contact-rich tasks is challenging and cannot be entirely solved using classical control approaches due to the difficulty of constructing an analytic description of the contact dynamics. Additionally, in a manipulation task like food-cutting, purely learning-based methods such as Reinforcement Learning, require either a vast amount of data that is expensive to collect on a real robot, or a highly realistic simulation environment, which is currently not available. This paper presents a data-driven control approach that employs a recurrent neural network to model the dynamics for a Model Predictive Controller. We extend on previous work that was limited to torque-controlled robots by incorporating Force/Torque sensor measurements and formulate the control problem so that it can be applied to the more common velocity controlled robots. We evaluate the performance on objects used for training, as well as on unknown objects, by means of the cutting rates achieved and demonstrate that the method can efficiently treat different cases with only one dynamic model. Finally we investigate the behavior of the system during force-critical instances of cutting and illustrate its adaptive behavior in difficult cases.
We develop a system for modeling hand-object interactions in 3D from RGB images that show a hand which is holding a novel object from a known category. We design a Convolutional Neural Network (CNN) for Hand-held Object Pose and Shape estimation called HOPS-Net and utilize prior work to estimate the hand pose and configuration. We leverage the insight that information about the hand facilitates object pose and shape estimation by incorporating the hand into both training and inference of the object pose and shape as well as the refinement of the estimated pose. The network is trained on a large synthetic dataset of objects in interaction with a human hand. To bridge the gap between real and synthetic images, we employ an image-to-image translation model (Augmented CycleGAN) that generates realistically textured objects given a synthetic rendering. This provides a scalable way of generating annotated data for training HOPS-Net. Our quantitative experiments show that even noisy hand parameters significantly help object pose and shape estimation. The qualitative experiments show results of pose and shape estimation of objects held by a hand "in the wild".
In collaborative tasks, people rely both on verbal and non-verbal cues simultaneously to communicate with each other. For human-robot interaction to run smoothly and naturally, a robot should be equipped with the ability to robustly disambiguate referring expressions. In this work, we propose a model that can disambiguate multimodal fetching requests using modalities such as head movements, hand gestures, and speech. We analysed the acquired data from mixed reality experiments and formulated a hypothesis that modelling temporal dependencies of events in these three modalities increases the model's predictive power. We evaluated our model on a Bayesian framework to interpret referring expressions with and without exploiting a temporal prior.
This paper presents an approach for learning invariant features for object affordance understanding. One of the major problems for a robotic agent acquiring a deeper understanding of affordances is finding sensory-grounded semantics. Being able to understand what in the representation of an object makes the object afford an action opens up for more efficient manipulation, interchange of objects that visually might not be similar, transfer learning, and robot to human communication. Our approach uses a metric learning algorithm that learns a feature transform that encourages objects that affords the same action to be close in the feature space. We regularize the learning, such that we penalize irrelevant features, allowing the agent to link what in the sensory input caused the object to afford the action. From this, we show how the agent can abstract the affordance and reason about the similarity between different affordances.
This paper addresses non-prehensile rearrangement planning problems where a robot is tasked to rearrange objects among obstacles on a planar surface. We present an efficient planning algorithm that is designed to impose few assumptions on the robot's non-prehensile manipulation abilities and is simple to adapt to different robot embodiments. For this, we combine sampling-based motion planning with reinforcement learning and generative modeling. Our algorithm explores the composite configuration space of objects and robot as a search over robot actions, forward simulated in a physics model. This search is guided by a generative model that provides robot states from which an object can be transported towards a desired state, and a learned policy that provides corresponding robot actions. As an efficient generative model, we apply Generative Adversarial Networks. We implement and evaluate our approach for robots endowed with configuration spaces in SE(2). We demonstrate empirically the efficacy of our algorithm design choices and observe more than 2x speedup in planning time on various test scenarios compared to a state-of-the-art approach.
Human activity modeling operates on two levels: high-level action modeling, such as classification, prediction, detection and anticipation, and low-level motion trajectory prediction and synthesis. In this work, we propose a semi-supervised generative latent variable model that addresses both of these levels by modeling continuous observations as well as semantic labels. We extend the model to capture the dependencies between different entities, such as a human and objects, and to represent hierarchical label structure, such as high-level actions and sub-activities. In the experiments we investigate our model's capability to classify, predict, detect and anticipate semantic action and affordance labels and to predict and generate human motion. We train our models on data extracted from depth image streams from the Cornell Activity 120, the UTKinect-Action3D and the Stony Brook University Kinect Interaction Dataset. We observe that our model performs well in all of the tasks and often outperforms task-specific models.
We develop an approach that benefits from large simulated datasets and takes full advantage of the limited online data that is most relevant. We propose a variant of Bayesian optimization that alternates between using informed and uninformed kernels. With this Bernoulli Alternation Kernel we ensure that discrepancies between simulation and reality do not hinder adapting robot control policies online. The proposed approach is applied to a challenging real-world problem of task-oriented grasping with novel objects. Our further contribution is a neural network architecture and training pipeline that use experience from grasping objects in simulation to learn grasp stability scores. We learn task scores from a labeled dataset with a convolutional network, which is used to construct an informed kernel for our variant of Bayesian optimization. Experiments on an ABB Yumi robot with real sensor data demonstrate success of our approach, despite the challenge of fulfilling task requirements and high uncertainty over physical properties of objects.
Successful Human-Robot collaboration requires a predictive model of human behavior. The robot needs to be able to recognize current goals and actions and to predict future activities in a given context. However, the spatio-temporal sequence of human actions is difficult to model since latent factors such as intention, task, knowledge, intuition and preference determine the action choices of each individual. In this work we introduce semi-supervised variational recurrent neural networks which are able to a) model temporal distributions over latent factors and the observable feature space, b) incorporate discrete labels such as activity type when available, and c) generate possible future action sequences on both feature and label level. We evaluate our model on the Cornell Activity Dataset CAD-120 dataset. Our model outperforms state-of-the-art approaches in both activity and affordance detection and anticipation. Additionally, we show how samples of possible future action sequences are in line with past observations.
Reinforcement Learning methods are capable of solving complex problems, but resulting policies might perform poorly in environments that are even slightly different. In robotics especially, training and deployment conditions often vary and data collection is expensive, making retraining undesirable. Simulation training allows for feasible training times, but on the other hand suffers from a reality-gap when applied in real-world settings. This raises the need of efficient adaptation of policies acting in new environments. We consider this as a problem of transferring knowledge within a family of similar Markov decision processes. For this purpose we assume that Q-functions are generated by some low-dimensional latent variable. Given such a Q-function, we can find a master policy that can adapt given different values of this latent variable. Our method learns both the generative mapping and an approximate posterior of the latent variables, enabling identification of policies for new tasks by searching only in the latent space, rather than the space of all policies. The low-dimensional space, and master policy found by our method enables policies to quickly adapt to new environments. We demonstrate the method on both a pendulum swing-up task in simulation, and for simulation-to-real transfer on a pushing task.