This report introduces our UniTeam agent - an improved baseline for the "HomeRobot: Open Vocabulary Mobile Manipulation" challenge. The challenge poses problems of navigation in unfamiliar environments, manipulation of novel objects, and recognition of open-vocabulary object classes. This challenge aims to facilitate cross-cutting research in embodied AI using recent advances in machine learning, computer vision, natural language, and robotics. In this work, we conducted an exhaustive evaluation of the provided baseline agent; identified deficiencies in perception, navigation, and manipulation skills; and improved the baseline agent's performance. Notably, enhancements were made in perception - minimizing misclassifications; navigation - preventing infinite loop commitments; picking - addressing failures due to changing object visibility; and placing - ensuring accurate positioning for successful object placement.
Reinforcement learning and Imitation Learning approaches utilize policy learning strategies that are difficult to generalize well with just a few examples of a task. In this work, we propose a language-conditioned semantic search-based method to produce an online search-based policy from the available demonstration dataset of state-action trajectories. Here we directly acquire actions from the most similar manipulation trajectories found in the dataset. Our approach surpasses the performance of the baselines on the CALVIN benchmark and exhibits strong zero-shot adaptation capabilities. This holds great potential for expanding the use of our online search-based policy approach to tasks typically addressed by Imitation Learning or Reinforcement Learning-based policies.
Tactile information is important for robust performance in robotic tasks that involve physical interaction, such as object manipulation. However, with more data included in the reasoning and control process, modeling behavior becomes increasingly difficult. Deep Reinforcement Learning (DRL) produced promising results for learning complex behavior in various domains, including tactile-based manipulation in robotics. In this work, we present our open-source reinforcement learning environments for the TIAGo service robot. They produce tactile sensor measurements that resemble those of a real sensorised gripper for TIAGo, encouraging research in transfer learning of DRL policies. Lastly, we show preliminary training results of a learned force control policy and compare it to a classical PI controller.
We present a holistic grasping controller, combining free-space position control and in-contact force-control for reliable grasping given uncertain object pose estimates. Employing tactile fingertip sensors, undesired object displacement during grasping is minimized by pausing the finger closing motion for individual joints on first contact until force-closure is established. While holding an object, the controller is compliant with external forces to avoid high internal object forces and prevent object damage. Gravity as an external force is explicitly considered and compensated for, thus preventing gravity-induced object drift. We evaluate the controller in two experiments on the TIAGo robot and its parallel-jaw gripper proving the effectiveness of the approach for robust grasping and minimizing object displacement. In a series of ablation studies, we demonstrate the utility of the individual controller components.
The advent of tactile sensors in robotics has sparked many ideas on how robots can leverage direct contact measurements of their environment interactions to improve manipulation tasks. An important line of research in this regard is that of grasp force control, which aims to manipulate objects safely by limiting the amount of force exerted on the object. While prior works have either hand-modeled their force controllers, employed model-based approaches, or have not shown sim-to-real transfer, we propose a model-free deep reinforcement learning approach trained in simulation and then transferred to the robot without further fine-tuning. We therefore present a simulation environment that produces realistic normal forces, which we use to train continuous force control policies. An evaluation in which we compare against a baseline and perform an ablation study shows that our approach outperforms the hand-modeled baseline and that our proposed inductive bias and domain randomization facilitate sim-to-real transfer. Code, models, and supplementary videos are available on https://sites.google.com/view/rl-force-ctrl
Tactile sensors are promising tools for endowing robots with embodied intelligence and increased dexterity. These sensors can provide robotic systems with direct information about physical interactions with the world, which is difficult to obtain from extrinsic perception systems. This work deals with a practical everyday living problem: stable object placement on flat surfaces starting from unknown initial poses. Common approaches for object placing either require complete scene specifications or indirect sensor measurements, such as cameras which are prone to suffer from occlusions. Instead, this work proposes a novel approach for stable object placing that combines tactile feedback and proprioceptive sensing. We devise a neural architecture that estimates a rotation matrix which results in a corrective gripper movement that aligns the object with the table and paves the way for the subsequent stable object placement. We compare models with different sensing modalities, such as force-torque and an external motion capture system, in real-world object placement tasks with different objects. Our experimental evaluation of the placing policies with a set of unknown everyday objects reveals an impressive generalization of the tactile-based pipeline and suggests that tactile sensing plays a vital role in the intrinsic understanding of dexterous object manipulation. Videos of our approach are available at https://sites.google.com/view/placing-by-touching.
Despite many advances in service robotics, successful and secure object manipulation on mobile platforms is still a challenge. In order to come closer to human grasping performance, it is natural to provide robots with the same capability that humans have: the sense of touch. This abstract presents novel, tactile-equipped end-effectors for the service robot TIAGo that are currently being developed. Their primary goal is to improve reliability and success of mobile manipulation, but they also enable further research in related fields such as learning by human demonstration, object exploration and force control algorithms.
When data are organized in matrices or arrays of higher dimensions (tensors), classical regression methods first transform these data into vectors, therefore ignoring the underlying structure of the data and increasing the dimensionality of the problem. This flattening operation typically leads to overfitting when only few training data is available. In this paper, we present a mixture of experts model that exploits tensorial representations for regression of tensor-valued data. The proposed formulation takes into account the underlying structure of the data and remains efficient when few training data are available. Evaluation on artificially generated data, as well as offline and real-time experiments recognizing hand movements from tactile myography prove the effectiveness of the proposed approach.
We have used a simple camera phone to significantly improve an `exploration system' for astrobiology and geology. This camera phone will make it much easier to develop and test computer-vision algorithms for future planetary exploration. We envision that the `Astrobiology Phone-cam' exploration system can be fruitfully used in other problem domains as well.
We present results from the first geological field tests of the `Cyborg Astrobiologist', which is a wearable computer and video camcorder system that we are using to test and train a computer-vision system towards having some of the autonomous decision-making capabilities of a field-geologist. The Cyborg Astrobiologist platform has thus far been used for testing and development of these algorithms and systems: robotic acquisition of quasi-mosaics of images, real-time image segmentation, and real-time determination of interesting points in the image mosaics. This work is more of a test of the whole system, rather than of any one part of the system. However, beyond the concept of the system itself, the uncommon map (despite its simplicity) is the main innovative part of the system. The uncommon map helps to determine interest-points in a context-free manner. Overall, the hardware and software systems function reliably, and the computer-vision algorithms are adequate for the first field tests. In addition to the proof-of-concept aspect of these field tests, the main result of these field tests is the enumeration of those issues that we can improve in the future, including: dealing with structural shadow and microtexture, and also, controlling the camera's zoom lens in an intelligent manner. Nonetheless, despite these and other technical inadequacies, this Cyborg Astrobiologist system, consisting of a camera-equipped wearable-computer and its computer-vision algorithms, has demonstrated its ability of finding genuinely interesting points in real-time in the geological scenery, and then gathering more information about these interest points in an automated manner. We use these capabilities for autonomous guidance towards geological points-of-interest.