We study $(\epsilon, \delta)$-PAC best arm identification, where a decision-maker must identify an $\epsilon$-optimal arm with probability at least $1 - \delta$, while minimizing the number of arm pulls (samples). Most of the work on this topic is in the sequential setting, where there is no constraint on the \emph{time} taken to identify such an arm; this allows the decision-maker to pull one arm at a time. In this work, the decision-maker is given a deadline of $T$ rounds, where, on each round, it can adaptively choose which arms to pull and how many times to pull them; this distinguishes the number of decisions made (i.e., time or number of rounds) from the number of samples acquired (cost). Such situations occur in clinical trials, where one may need to identify a promising treatment under a deadline while minimizing the number of test subjects, or in simulation-based studies run on the cloud, where we can elastically scale up or down the number of virtual machines to conduct as many experiments as we wish, but need to pay for the resource-time used. As the decision-maker can only make $T$ decisions, she may need to pull some arms excessively relative to a sequential algorithm in order to perform well on all possible problems. We formalize this added difficulty with two hardness results that indicate that unlike sequential settings, the ability to adapt to the problem difficulty is constrained by the finite deadline. We propose Elastic Batch Racing (EBR), a novel algorithm for this setting and bound its sample complexity, showing that EBR is optimal with respect to both hardness results. We present simulations evaluating EBR in this setting, where it outperforms baselines by several orders of magnitude.
Disentangling two or more cables requires many steps to remove crossings between and within cables. We formalize the problem of disentangling multiple cables and present an algorithm, Iterative Reduction Of Non-planar Multiple cAble kNots (IRON-MAN), that outputs robot actions to remove crossings from multi-cable knotted structures. We instantiate this algorithm with a learned perception system, inspired by prior work in single-cable untying that given an image input, can disentangle two-cable twists, three-cable braids, and knots of two or three cables, such as overhand, square, carrick bend, sheet bend, crown, and fisherman's knots. IRON-MAN keeps track of task-relevant keypoints corresponding to target cable endpoints and crossings and iteratively disentangles the cables by identifying and undoing crossings that are critical to knot structure. Using a da Vinci surgical robot, we experimentally evaluate the effectiveness of IRON-MAN on untangling multi-cable knots of types that appear in the training data, as well as generalizing to novel classes of multi-cable knots. Results suggest that IRON-MAN is effective in disentangling knots involving up to three cables with 80.5% success and generalizing to knot types that are not present during training, with cables of both distinct or identical colors.
Corrective interventions while a robot is learning to automate a task provide an intuitive method for a human supervisor to assist the robot and convey information about desired behavior. However, these interventions can impose significant burden on a human supervisor, as each intervention interrupts other work the human is doing, incurs latency with each context switch between supervisor and autonomous control, and requires time to perform. We present LazyDAgger, which extends the interactive imitation learning (IL) algorithm SafeDAgger to reduce context switches between supervisor and autonomous control. We find that LazyDAgger improves the performance and robustness of the learned policy during both learning and execution while limiting burden on the supervisor. Simulation experiments suggest that LazyDAgger can reduce context switches by an average of 60% over SafeDAgger on 3 continuous control tasks while maintaining state-of-the-art policy performance. In physical fabric manipulation experiments with an ABB YuMi robot, LazyDAgger reduces context switches by 60% while achieving a 60% higher success rate than SafeDAgger at execution time.
We consider the automation of the well-known peg-transfer task from the Fundamentals of Laparoscopic Surgery (FLS). While human surgeons teleoperate robots to perform this task with great dexterity, it remains challenging to automate. We present an approach that leverages emerging innovations in depth sensing, deep learning, and Peiper's method for computing inverse kinematics with time-minimized joint motion. We use the da Vinci Research Kit (dVRK) surgical robot with a Zivid depth sensor, and automate three variants of the peg-transfer task: unilateral, bilateral without handovers, and bilateral with handovers. We use 3D-printed fiducial markers with depth sensing and a deep recurrent neural network to improve the precision of the dVRK to less than 1 mm. We report experimental results for 1800 block transfer trials. Results suggest that the fully automated system can outperform an experienced human surgical resident, who performs far better than untrained humans, in terms of both speed and success rate. For the most difficult variant of peg transfer (with handovers) we compare the performance of the surgical resident with performance of the automated system over 120 trials for each. The experienced surgical resident achieves success rate 93.2 % with mean transfer time of 8.6 seconds. The automated system achieves success rate 94.1 % with mean transfer time of 8.1 seconds. To our knowledge this is the first fully automated system to achieve "superhuman" performance in both speed and success on peg transfer. Supplementary material is available at https://sites.google.com/view/surgicalpegtransfer.
Automation of surgical tasks using cable-driven robots is challenging due to backlash, hysteresis, and cable tension, and these issues are exacerbated as surgical instruments must often be changed during an operation. In this work, we propose a framework for automation of high-precision surgical tasks by learning sample efficient, accurate, closed-loop policies that operate directly on visual feedback instead of robot encoder estimates. This framework, which we call intermittent visual servoing (IVS), intermittently switches to a learned visual servo policy for high-precision segments of repetitive surgical tasks while relying on a coarse open-loop policy for the segments where precision is not necessary. To compensate for cable-related effects, we apply imitation learning to rapidly train a policy that maps images of the workspace and instrument from a top-down RGB camera to small corrective motions. We train the policy using only 180 human demonstrations that are roughly 2 seconds each. Results on a da Vinci Research Kit suggest that combining the coarse policy with half a second of corrections from the learned policy during each high-precision segment improves the success rate on the Fundamentals of Laparoscopic Surgery peg transfer task from 72.9% to 99.2%, 31.3% to 99.2%, and 47.2% to 100.0% for 3 instruments with differing cable-related effects. In the contexts we studied, IVS attains the highest published success rates for automated surgical peg transfer and is significantly more reliable than previous techniques when instruments are changed. Supplementary material is available at https://tinyurl.com/ivs-icra.
Untangling ropes, wires, and cables is a challenging task for robots due to the high-dimensional configuration space, visual homogeneity, self-occlusions, and complex dynamics. We consider dense (tight) knots that lack space between self-intersections and present an iterative approach that uses learned geometric structure in configurations. We instantiate this into an algorithm, HULK: Hierarchical Untangling from Learned Keypoints, which combines learning-based perception with a geometric planner into a policy that guides a bilateral robot to untangle knots. To evaluate the policy, we perform experiments both in a novel simulation environment modelling cables with varied knot types and textures and in a physical system using the da Vinci surgical robot. We find that HULK is able to untangle cables with dense figure-eight and overhand knots and generalize to varied textures and appearances. We compare two variants of HULK to three baselines and observe that HULK achieves 43.3% higher success rates on a physical system compared to the next best baseline. HULK successfully untangles a cable from a dense initial configuration containing up to two overhand and figure-eight knots in 97.9% of 378 simulation experiments with an average of 12.1 actions per trial. In physical experiments, HULK achieves 61.7% untangling success, averaging 8.48 actions per trial. Supplementary material, code, and videos can be found at https://tinyurl.com/y3a88ycu.
We study exploration in stochastic multi-armed bandits when we have access to a divisible resource, and can allocate varying amounts of this resource to arm pulls. By allocating more resources to a pull, we can compute the outcome faster to inform subsequent decisions about which arms to pull. However, since distributed environments do not scale linearly, executing several arm pulls in parallel, and hence less resources per pull, may result in better throughput. For example, in simulation-based scientific studies, an expensive simulation can be sped up by running it on multiple cores. This speed-up is, however, partly offset by the communication among cores and overheads, which results in lower throughput than if fewer cores were allocated to run more trials in parallel. We explore these trade-offs in the fixed confidence setting, where we need to find the best arm with a given success probability, while minimizing the time to do so. We propose an algorithm which trades off between information accumulation and throughout and show that the time taken can be upper bounded by the solution of a dynamic program whose inputs are the squared gaps between the suboptimal and optimal arms. We prove a matching hardness result which demonstrates that the above dynamic program is fundamental to this problem. Next, we propose and analyze an algorithm for the fixed deadline setting, where we are given a time deadline and need to maximize the success probability of finding the best arm. We corroborate these theoretical insights with an empirical evaluation.
Safety remains a central obstacle preventing widespread use of RL in the real world: learning new tasks in uncertain environments requires extensive exploration, but safety requires limiting exploration. We propose Recovery RL, an algorithm which navigates this tradeoff by (1) leveraging offline data to learn about constraint violating zones before policy learning and (2) separating the goals of improving task performance and constraint satisfaction across two policies: a task policy that only optimizes the task reward and a recovery policy that guides the agent to safety when constraint violation is likely. We evaluate Recovery RL on 6 simulation domains, including two contact-rich manipulation tasks and an image-based navigation task, and an image-based obstacle avoidance task on a physical robot. We compare Recovery RL to 5 prior safe RL methods which jointly optimize for task performance and safety via constrained optimization or reward shaping and find that Recovery RL outperforms the next best prior method across all domains. Results suggest that Recovery RL trades off constraint violations and task successes 2 - 80 times more efficiently in simulation domains and 3 times more efficiently in physical experiments. See https://tinyurl.com/rl-recovery for videos and supplementary material.
We explore learning pixelwise correspondences between images of deformable objects in different configurations. Traditional correspondence matching approaches such as SIFT, SURF, and ORB can fail to provide sufficient contextual information for fine-grained manipulation. We propose Multi-Modal Gaussian Shape Descriptor (MMGSD), a new visual representation of deformable objects which extends ideas from dense object descriptors to predict all symmetric correspondences between different object configurations. MMGSD is learned in a self-supervised manner from synthetic data and produces correspondence heatmaps with measurable uncertainty. In simulation, experiments suggest that MMGSD can achieve an RMSE of 32.4 and 31.3 for square cloth and braided synthetic nylon rope respectively. The results demonstrate an average of 47.7% improvement over a provided baseline based on contrastive learning, symmetric pixel-wise contrastive loss (SPCL), as opposed to MMGSD which enforces distributional continuity.
Robotic fabric manipulation is challenging due to the infinite dimensional configuration space and complex dynamics. In this paper, we learn visual representations of deformable fabric by training dense object descriptors that capture correspondences across images of fabric in various configurations. The learned descriptors capture higher level geometric structure, facilitating design of explainable policies. We demonstrate that the learned representation facilitates multistep fabric smoothing and folding tasks on two real physical systems, the da Vinci surgical robot and the ABB YuMi given high level demonstrations from a supervisor. The system achieves a 78.8% average task success rate across six fabric manipulation tasks. See https://tinyurl.com/fabric-descriptors for supplementary material and videos.