The acoustic response of an object can reveal a lot about its global state, for example its material properties or the extrinsic contacts it is making with the world. In this work, we build an active acoustic sensing gripper equipped with two piezoelectric fingers: one for generating signals, the other for receiving them. By sending an acoustic vibration from one finger to the other through an object, we gain insight into an object’s acoustic properties and contact state. We use this system to classify objects, estimate grasping position, estimate poses of internal structures, and classify the types of extrinsic contacts an object is making with the environment. Using our contact type classification model, we tackle a standard long-horizon manipulation problem: peg insertion. We use a simple simulated transition model based on the performance of our sensor to train an imitation learning policy that is robust to imperfect predictions from the classifier. We finally demonstrate the policy on a UR5 robot with active acoustic sensing as the only feedback. Videos can be found at https://roamlab.github.io/vibecheck.

Meta-World is widely used for evaluating multi-task and meta-reinforcement learning agents, which are challenged to master diverse skills simultaneously. Since its introduction however, there have been numerous undocumented changes which inhibit a fair comparison of algorithms. This work strives to disambiguate these results from the literature, while also leveraging the past versions of Meta-World to provide insights into multi-task and meta-reinforcement learning benchmark design. Through this process we release an open-source version of Meta-World that has full reproducibility of past results, is more technically ergonomic, and gives users more control over the tasks that are included in a task set.

We introduce MORPH, a method for co-optimization of hardware design parameters and control policies in simulation using reinforcement learning. Like most co-optimization methods, MORPH relies on a model of the hardware being optimized, usually simulated based on the laws of physics. However, such a model is often difficult to integrate into an effective optimization routine. To address this, we introduce a proxy hardware model, which is always differentiable and enables efficient co-optimization alongside a long-horizon control policy using RL. MORPH is designed to ensure that the optimized hardware proxy remains as close as possible to its realistic counterpart, while still enabling task completion. We demonstrate our approach on simulated 2D reaching and 3D multi-fingered manipulation tasks.

In a Human-in-the-Loop paradigm, a robotic agent is able to act mostly autonomously in solving a task, but can request help from an external expert when needed. However, knowing when to request such assistance is critical: too few requests can lead to the robot making mistakes, but too many requests can overload the expert. In this paper, we present a Reinforcement Learning based approach to this problem, where a semi-autonomous agent asks for external assistance when it has low confidence in the eventual success of the task. The confidence level is computed by estimating the variance of the return from the current state. We show that this estimate can be iteratively improved during training using a Bellman-like recursion. On discrete navigation problems with both fully-and partially-observable state information, we show that our method makes effective use of a limited budget of expert calls at run-time, despite having no access to the expert at training time.

Underactuated manipulators reduce the number of bulky motors, thereby enabling compact and mechanically robust designs. However, fewer actuators than joints means that the manipulator can only access a specific manifold within the joint space, which is particular to a given hardware configuration and can be low-dimensional and/or discontinuous. Determining an appropriate set of hardware parameters for this class of mechanisms, therefore, is difficult - even for traditional task-based co-optimization methods. In this paper, our goal is to implement a task-based design and policy co-optimization method for underactuated, tendon-driven manipulators. We first formulate a general model for an underactuated, tendon-driven transmission. We then use this model to co-optimize a three-link, two-actuator kinematic chain using reinforcement learning. We demonstrate that our optimized tendon transmission and control policy can be transferred reliably to physical hardware with real-world reaching experiments.

The choice of a grasp plays a critical role in the success of downstream manipulation tasks. Consider a task of placing an object in a cluttered scene; the majority of possible grasps may not be suitable for the desired placement. In this paper, we study the synergy between the picking and placing of an object in a cluttered scene to develop an algorithm for task-aware grasp estimation. We present an object-centric action space that encodes the relationship between the geometry of the placement scene and the object to be placed in order to provide placement affordance maps directly from perspective views of the placement scene. This action space enables the computation of a one-to-one mapping between the placement and picking actions allowing the robot to generate a diverse set of pick-and-place proposals and to optimize for a grasp under other task constraints such as robot kinematics and collision avoidance. With experiments both in simulation and on a real robot we demonstrate that with our method, the robot is able to successfully complete the task of placement-aware grasping with over 89 % accuracy in such a way that generalizes to novel objects and scenes.

Controlling robotic manipulators with high-dimensional action spaces for dexterous tasks is a challenging problem. Inspired by human manipulation, researchers have studied generating and using postural synergies for robot hands to accomplish manipulation tasks, leveraging the lower dimensional nature of synergistic action spaces. However, many of these works require pre-collected data from an existing controller in order to derive such a subspace by means of dimensionality reduction. In this paper, we present a framework that simultaneously discovers both a synergy space and a multi-task policy that operates on this low-dimensional action space to accomplish diverse manipulation tasks. We demonstrate that our end-to-end method is able to perform multiple tasks using few synergies, and outperforms sequential methods that apply dimensionality reduction to independently collected data. We also show that deriving synergies using multiple tasks can lead to a subspace that enables robots to efficiently learn new manipulation tasks and interactions with new objects.

Recent advances in deep reinforcement learning (RL) have demonstrated its potential to learn complex robotic manipulation tasks. However, RL still requires the robot to collect a large amount of real-world experience. To address this problem, recent works have proposed learning from expert demonstrations (LfD), particularly via inverse reinforcement learning (IRL), given its ability to achieve robust performance with only a small number of expert demonstrations. Nevertheless, deploying IRL on real robots is still challenging due to the large number of robot experiences it requires. This paper aims to address this scalability challenge with a robust, sample-efficient, and general meta-IRL algorithm, SQUIRL, that performs a new but related long-horizon task robustly given only a single video demonstration. First, this algorithm bootstraps the learning of a task encoder and a task-conditioned policy using behavioral cloning (BC). It then collects real-robot experiences and bypasses reward learning by directly recovering a Q-function from the combined robot and expert trajectories. Next, this algorithm uses the learned Q-function to re-evaluate all cumulative experiences collected by the robot to improve the policy quickly. In the end, the policy performs more robustly (90%+ success) than BC on new tasks while requiring no experiences at test time. Finally, our real-robot and simulated experiments demonstrate our algorithm's generality across different state spaces, action spaces, and vision-based manipulation tasks, e.g., pick-pour-place and pick-carry-drop.

With the increasing complexity of tasks that are crowdsourced, requesters need to form teams of professional workers that can satisfy complex task skill requirements. Team crowdsourcing in social networks (SNs) provides a promising solution for complex task crowdsourcing, where the requester hires a team of professional workers that are also socially connected can work together collaboratively. Previous social team formation approaches have mainly focused on the algorithmic aspect for social welfare maximization; however, within the traditional objective of maximizing social welfare alone, selfish workers can manipulate the crowdsourcing market by behaving untruthfully. This dishonest behavior discourages other workers from participating and is unprofitable for the requester. To address this strategic social team crowdsourcing problem, truthful mechanisms are developed to guarantee that a worker's utility is optimized when he behaves honestly. This problem is proved to NP-hard, and two efficient mechanisms are proposed to optimize social welfare while reducing time complexity for different scale applications. For small-scale applications where the task requires a small number of skills, a binary tree network is first extracted from the social network, and a dynamic programming-based optimal team is formed in the binary tree. For large-scale applications where the task requires a large number of skills, a team is formed greedily based on the workers' social structure, skill, and working cost. For both mechanisms, the threshold payment rule, which pays each worker his marginal value for task completion, is proposed to elicit truthfulness. Finally, the experimental results of a real-world dataset show that compared to the benchmark exponential VCG truthful mechanism, the proposed small-scale-oriented mechanism can reduce computation time while producing nearly the same social welfare results. Furthermore, compared to other state-of-the-art polynomial heuristics, the proposed large-scale-oriented mechanism can achieve truthfulness while generating better social welfare outcomes.