Reinforcement Learning (RL) has the potential to enable robots to learn from their own actions in the real world. Unfortunately, RL can be prohibitively expensive, in terms of on-robot runtime, due to inefficient exploration when learning from a sparse reward signal. Designing dense reward functions is labour-intensive and requires domain expertise. In our work, we propose Goal-Contrastive Rewards (GCR), a dense reward function learning method that can be trained on passive video demonstrations. By using videos without actions, our method is easier to scale, as we can use arbitrary videos. GCR combines two loss functions, an implicit value loss function that models how the reward increases when traversing a successful trajectory, and a goal-contrastive loss that discriminates between successful and failed trajectories. We perform experiments in simulated manipulation environments across RoboMimic and MimicGen tasks, as well as in the real world using a Franka arm and a Spot quadruped. We find that GCR leads to a more-sample efficient RL, enabling model-free RL to solve about twice as many tasks as our baseline reward learning methods. We also demonstrate positive cross-embodiment transfer from videos of people and of other robots performing a task. Website: https://gcr-robot.github.io/.

Despite outstanding semantic scene segmentation in closed-worlds, deep neural networks segment novel instances poorly, which is required for autonomous agents acting in an open world. To improve out-of-distribution (OOD) detection for segmentation, we introduce a metacognitive approach in the form of a lightweight module that leverages entropy measures, segmentation predictions, and spatial context to characterize the segmentation model’s uncertainty and detect pixel-wise OOD data in real-time. Additionally, our approach incorporates a novel method of generating synthetic OOD data in context with in-distribution data, which we use to fine-tune existing segmentation models with maximum entropy training. This further improves the metacognitive module’s performance without requiring access to OOD data while enabling compatibility with established pre-trained models. Our resulting approach can reliably detect OOD instances in a scene, as shown by state-of-the-art performance on OOD detection for semantic segmentation benchmarks.

We introduce Equivariant Neural Field Expectation Maximization (EFEM), a simple, effective, and robust geometric algorithm that can segment objects in 3D scenes without annotations or training on scenes. We achieve such unsupervised segmentation by exploiting single object shape priors. We make two novel steps in that direction. First, we introduce equivariant shape representations to this problem to eliminate the complexity induced by the variation in object configuration. Second, we propose a novel EM algorithm that can iteratively refine segmentation masks using the equivariant shape prior. We collect a novel real dataset Chairs and Mugs that contains various object configurations and novel scenes in order to verify the effectiveness and robustness of our method. Experimental results demonstrate that our method achieves consistent and robust performance across different scenes where the (weakly) supervised methods may fail. Code and data available at https://www.cis.upenn.edu/~leijh/projects/EFEM

We consider the problem of Vision-and-Language Navigation (VLN). The majority of current methods for VLN are trained end-to-end using either unstructured memory such as LSTM, or using cross-modal attention over the egocentric observations of the agent. In contrast to other works, our key insight is that the association between language and vision is stronger when it occurs in explicit spatial representations. In this work, we propose a cross-modal map learning model for vision-and-language navigation that first learns to predict the top-down semantics on an egocentric map for both observed and unobserved regions, and then predicts a path towards the goal as a set of way-points. In both cases, the prediction is informed by the language through cross-modal attention mechanisms. We experimentally test the basic hypothesis that language-driven navigation can be solved given a map, and then show competitive results on the full VLN-CE benchmark.

We consider the problems of exploration and pointgoal navigation in previously unseen environments, where the spatial complexity of indoor scenes and partial observability constitute these tasks challenging. We argue that learning occupancy priors over indoor maps provides significant advantages towards addressing these problems. To this end, we present a novel planning framework that first learns to generate occupancy maps beyond the field-of-view of the agent, and second leverages the model uncertainty over the generated areas to formulate path selection policies for each task of interest. For pointgoal navigation the policy chooses paths with an upper confidence bound policy for efficient and traversable paths, while for exploration the policy maximizes model uncertainty over candidate paths. We perform experiments in the visually realistic environments of Matterport3D using the Habitat simulator and demonstrate: 1) Improved results on exploration and map quality metrics over competitive methods, and 2) The effectiveness of our planning module when paired with the state-of-the-art DD-PPO method for the point-goal navigation task.

In order to interact with the world, agents must be able to predict the results of the world’s dynamics. A natural approach to learn about these dynamics is through video prediction, as cameras are ubiquitous and powerful sensors. Direct pixel-to-pixel video prediction is difficult, does not take advantage of known priors, and does not provide an easy interface to utilize the learned dynamics. Object-centric video prediction offers a solution to these problems by taking advantage of the simple prior that the world is made of objects and by providing a more natural interface for control. However, existing object-centric video prediction pipelines require dense object annotations in training video sequences. In this work, we present Object-centric Prediction without Annotation (OPA), an object-centric video prediction method that takes advantage of priors from powerful computer vision models. We validate our method on a dataset comprised of video sequences of stacked objects falling, and demonstrate how to adapt a perception model in an environment through end-to-end video prediction training.

We propose a framework for deformable linear object prediction. Prediction of deformable objects (e.g., rope) is challenging due to their non-linear dynamics and infinite-dimensional configuration spaces. By mapping the dynamics from a non-linear space to a linear space, we can use the good properties of linear dynamics for easier learning and more efficient prediction. We learn a locally linear, action-conditioned dynamics model that can be used to predict future latent states. Then, we decode the predicted latent state into the predicted state. We also apply a sampling-based optimization algorithm to select the optimal control action. We empirically demonstrate that our approach can predict the rope state accurately up to ten steps into the future and that our algorithm can find the optimal action given an initial state and a goal state.

Collecting new experience is costly in many robotic tasks, so determining how to efficiently explore in a new environment to learn as much as possible in as few trials as possible is an important problem for robotics. In this paper, we propose a method for exploring for the purpose of learning a dynamics model. Our key idea is to minimize a score given by a discriminator network as an objective for a planner which chooses actions. This discriminator is optimized jointly with a prediction model and enables our active learning approach to sample sequences of observations and actions which result in predictions considered the least realistic by the discriminator. Comparable existing exploration methods cannot operate in many prediction-planning pipelines used in robotic learning without hardware modifications to standard robotics platforms in order to accommodate their large compute requirements, so the primary contribution of our adversarial exploration method is scalability. We demonstrate progressively increased performance of our adversarial exploration approach compared to leading model-based exploration strategies as compute is restricted in simulated environments. We further demonstrate the ability of our adversarial method to scale to a robotic manipulation prediction-planning pipeline where we improve sample efficiency and prediction performance for a domain transfer problem.