Imitation learning requires high-quality demonstrations consisting of sequences of state-action pairs. For contact-rich dexterous manipulation tasks that require fine-grained dexterity, the actions in these state-action pairs must produce the right forces. Current widely-used methods for collecting dexterous manipulation demonstrations are difficult to use for demonstrating contact-rich tasks due to unintuitive human-to-robot motion retargeting and the lack of direct haptic feedback. Motivated by this, we propose DexForce, a method for collecting demonstrations of contact-rich dexterous manipulation. DexForce leverages contact forces, measured during kinesthetic demonstrations, to compute force-informed actions for policy learning. We use DexForce to collect demonstrations for six tasks and show that policies trained on our force-informed actions achieve an average success rate of 76% across all tasks. In contrast, policies trained directly on actions that do not account for contact forces have near-zero success rates. We also conduct a study ablating the inclusion of force data in policy observations. We find that while using force data never hurts policy performance, it helps the most for tasks that require an advanced level of precision and coordination, like opening an AirPods case and unscrewing a nut.

In reinforcement learning, classic on-policy evaluation methods often suffer from high variance and require massive online data to attain the desired accuracy. Previous studies attempt to reduce evaluation variance by searching for or designing proper behavior policies to collect data. However, these approaches ignore the safety of such behavior policies -- the designed behavior policies have no safety guarantee and may lead to severe damage during online executions. In this paper, to address the challenge of reducing variance while ensuring safety simultaneously, we propose an optimal variance-minimizing behavior policy under safety constraints. Theoretically, while ensuring safety constraints, our evaluation method is unbiased and has lower variance than on-policy evaluation. Empirically, our method is the only existing method to achieve both substantial variance reduction and safety constraint satisfaction. Furthermore, we show our method is even superior to previous methods in both variance reduction and execution safety.

Policy evaluation estimates the performance of a policy by (1) collecting data from the environment and (2) processing raw data into a meaningful estimate. Due to the sequential nature of reinforcement learning, any improper data-collecting policy or data-processing method substantially deteriorates the variance of evaluation results over long time steps. Thus, policy evaluation often suffers from large variance and requires massive data to achieve the desired accuracy. In this work, we design an optimal combination of data-collecting policy and data-processing baseline. Theoretically, we prove our doubly optimal policy evaluation method is unbiased and guaranteed to have lower variance than previously best-performing methods. Empirically, compared with previous works, we show our method reduces variance substantially and achieves superior empirical performance.

We introduce AO-Grasp, a grasp proposal method that generates stable and actionable 6 degree-of-freedom grasps for articulated objects. Our generated grasps enable robots to interact with articulated objects, such as opening and closing cabinets and appliances. Given a segmented partial point cloud of a single articulated object, AO-Grasp predicts the best grasp points on the object with a novel Actionable Grasp Point Predictor model and then finds corresponding grasp orientations for each point by leveraging a state-of-the-art rigid object grasping method. We train AO-Grasp on our new AO-Grasp Dataset, which contains 48K actionable parallel-jaw grasps on synthetic articulated objects. In simulation, AO-Grasp achieves higher grasp success rates than existing rigid object grasping and articulated object interaction baselines on both train and test categories. Additionally, we evaluate AO-Grasp on 120 realworld scenes of objects with varied geometries, articulation axes, and joint states, where AO-Grasp produces successful grasps on 67.5% of scenes, while the baseline only produces successful grasps on 33.3% of scenes.

We present a large empirical investigation on the use of pre-trained visual representations (PVRs) for training downstream policies that execute real-world tasks. Our study spans five different PVRs, two different policy-learning paradigms (imitation and reinforcement learning), and three different robots for 5 distinct manipulation and indoor navigation tasks. From this effort, we can arrive at three insights: 1) the performance trends of PVRs in the simulation are generally indicative of their trends in the real world, 2) the use of PVRs enables a first-of-its-kind result with indoor ImageNav (zero-shot transfer to a held-out scene in the real world), and 3) the benefits from variations in PVRs, primarily data-augmentation and fine-tuning, also transfer to the real-world performance. See project website for additional details and visuals.

We present the largest and most comprehensive empirical study of pre-trained visual representations (PVRs) or visual 'foundation models' for Embodied AI. First, we curate CortexBench, consisting of 17 different tasks spanning locomotion, navigation, dexterous, and mobile manipulation. Next, we systematically evaluate existing PVRs and find that none are universally dominant. To study the effect of pre-training data scale and diversity, we combine over 4,000 hours of egocentric videos from 7 different sources (over 5.6M images) and ImageNet to train different-sized vision transformers using Masked Auto-Encoding (MAE) on slices of this data. Contrary to inferences from prior work, we find that scaling dataset size and diversity does not improve performance universally (but does so on average). Our largest model, named VC-1, outperforms all prior PVRs on average but does not universally dominate either. Finally, we show that task or domain-specific adaptation of VC-1 leads to substantial gains, with VC-1 (adapted) achieving competitive or superior performance than the best known results on all of the benchmarks in CortexBench. These models required over 10,000 GPU-hours to train and can be found on our website for the benefit of the research community.

Robots deployed in human-centric environments may need to manipulate a diverse range of articulated objects, such as doors, dishwashers, and cabinets. Articulated objects often come with unexpected articulation mechanisms that are inconsistent with categorical priors: for example, a drawer might rotate about a hinge joint instead of sliding open. We propose a category-independent framework for predicting the articulation models of unknown objects from sequences of RGB-D images. The prediction is performed by a two-step process: first, a visual perception module tracks object part poses from raw images, and second, a factor graph takes these poses and infers the articulation model including the current configuration between the parts as a 6D twist. We also propose a manipulation-oriented metric to evaluate predicted joint twists in terms of how well a compliant robot controller would be able to manipulate the articulated object given the predicted twist. We demonstrate that our visual perception and factor graph modules outperform baselines on simulated data and show the applicability of our factor graph on real world data.