Interactive Visual Grounding of Referring Expressions for Human-Robot Interaction

This paper presents INGRESS, a robot system that follows human natural language instructions to pick and place everyday objects. The core issue here is the grounding of referring expressions: infer objects and their relationships from input images and language expressions. INGRESS allows for unconstrained object categories and unconstrained language expressions. Further, it asks questions to disambiguate referring expressions interactively. To achieve these, we take the approach of grounding by generation and propose a two-stage neural network model for grounding. The first stage uses a neural network to generate visual descriptions of objects, compares them with the input language expression, and identifies a set of candidate objects. The second stage uses another neural network to examine all pairwise relations between the candidates and infers the most likely referred object. The same neural networks are used for both grounding and question generation for disambiguation. Experiments show that INGRESS outperformed a state-of-the-art method on the RefCOCO dataset and in robot experiments with humans.

HyP-DESPOT: A Hybrid Parallel Algorithm for Online Planning under Uncertainty

Planning under uncertainty is critical for robust robot performance in uncertain, dynamic environments, but it incurs high computational cost. State-of-the-art online search algorithms, such as DESPOT, have vastly improved the computational efficiency of planning under uncertainty and made it a valuable tool for robotics in practice. This work takes one step further by leveraging both CPU and GPU parallelization in order to achieve near real-time online planning performance for complex tasks with large state, action, and observation spaces. Specifically, we propose Hybrid Parallel DESPOT (HyP-DESPOT), a massively parallel online planning algorithm that integrates CPU and GPU parallelism in a multi-level scheme. It performs parallel DESPOT tree search by simultaneously traversing multiple independent paths using multi-core CPUs and performs parallel Monte-Carlo simulations at the leaf nodes of the search tree using GPUs. Experimental results show that HyP-DESPOT speeds up online planning by up to several hundred times, compared with the original DESPOT algorithm, in several challenging robotic tasks in simulation.

QMDP-Net: Deep Learning for Planning under Partial Observability

This paper introduces the QMDP-net, a neural network architecture for planning under partial observability. The QMDP-net combines the strengths of model-free learning and model-based planning. It is a recurrent policy network, but it represents a policy for a parameterized set of tasks by connecting a model with a planning algorithm that solves the model, thus embedding the solution structure of planning in a network learning architecture. The QMDP-net is fully differentiable and allows for end-to-end training. We train a QMDP-net on different tasks so that it can generalize to new ones in the parameterized task set and "transfer" to other similar tasks beyond the set. In preliminary experiments, QMDP-net showed strong performance on several robotic tasks in simulation. Interestingly, while QMDP-net encodes the QMDP algorithm, it sometimes outperforms the QMDP algorithm in the experiments, as a result of end-to-end learning.

Intention-Net: Integrating Planning and Deep Learning for Goal-Directed Autonomous Navigation

How can a delivery robot navigate reliably to a destination in a new office building, with minimal prior information? To tackle this challenge, this paper introduces a two-level hierarchical approach, which integrates model-free deep learning and model-based path planning. At the low level, a neural-network motion controller, called the intention-net, is trained end-to-end to provide robust local navigation. The intention-net maps images from a single monocular camera and "intentions" directly to robot controls. At the high level, a path planner uses a crude map, e.g., a 2-D floor plan, to compute a path from the robot's current location to the goal. The planned path provides intentions to the intention-net. Preliminary experiments suggest that the learned motion controller is robust against perceptual uncertainty and by integrating with a path planner, it generalizes effectively to new environments and goals.

DESPOT: Online POMDP Planning with Regularization

The partially observable Markov decision process (POMDP) provides a principled general framework for planning under uncertainty, but solving POMDPs optimally is computationally intractable, due to the "curse of dimensionality" and the "curse of history". To overcome these challenges, we introduce the Determinized Sparse Partially Observable Tree (DESPOT), a sparse approximation of the standard belief tree, for online planning under uncertainty. A DESPOT focuses online planning on a set of randomly sampled scenarios and compactly captures the "execution" of all policies under these scenarios. We show that the best policy obtained from a DESPOT is near-optimal, with a regret bound that depends on the representation size of the optimal policy. Leveraging this result, we give an anytime online planning algorithm, which searches a DESPOT for a policy that optimizes a regularized objective function. Regularization balances the estimated value of a policy under the sampled scenarios and the policy size, thus avoiding overfitting. The algorithm demonstrates strong experimental results, compared with some of the best online POMDP algorithms available. It has also been incorporated into an autonomous driving system for real-time vehicle control. The source code for the algorithm is available online.

Mathematical Models of Adaptation in Human-Robot Collaboration

A robot operating in isolation needs to reason over the uncertainty in its model of the world and adapt its own actions to account for this uncertainty. Similarly, a robot interacting with people needs to reason over its uncertainty over the human internal state, as well as over how this state may change, as humans adapt to the robot. This paper summarizes our own work in this area, which depicts the different ways that probabilistic planning and game-theoretic algorithms can enable such reasoning in robotic systems that collaborate with people. We start with a general formulation of the problem as a two-player game with incomplete information. We then articulate the different assumptions within this general formulation, and we explain how these lead to exciting and diverse robot behaviors in real-time interactions with actual human subjects, in a variety of manufacturing, personal robotics and assistive care settings.

Grounding Spatio-Semantic Referring Expressions for Human-Robot Interaction

The human language is one of the most natural interfaces for humans to interact with robots. This paper presents a robot system that retrieves everyday objects with unconstrained natural language descriptions. A core issue for the system is semantic and spatial grounding, which is to infer objects and their spatial relationships from images and natural language expressions. We introduce a two-stage neural-network grounding pipeline that maps natural language referring expressions directly to objects in the images. The first stage uses visual descriptions in the referring expressions to generate a candidate set of relevant objects. The second stage examines all pairwise relationships between the candidates and predicts the most likely referred object according to the spatial descriptions in the referring expressions. A key feature of our system is that by leveraging a large dataset of images labeled with text descriptions, it allows unrestricted object types and natural language referring expressions. Preliminary results indicate that our system outperforms a near state-of-the-art object comprehension system on standard benchmark datasets. We also present a robot system that follows voice commands to pick and place previously unseen objects.

Human-Robot Mutual Adaptation in Shared Autonomy

Shared autonomy integrates user input with robot autonomy in order to control a robot and help the user to complete a task. Our work aims to improve the performance of such a human-robot team: the robot tries to guide the human towards an effective strategy, sometimes against the human's own preference, while still retaining his trust. We achieve this through a principled human-robot mutual adaptation formalism. We integrate a bounded-memory adaptation model of the human into a partially observable stochastic decision model, which enables the robot to adapt to an adaptable human. When the human is adaptable, the robot guides the human towards a good strategy, maybe unknown to the human in advance. When the human is stubborn and not adaptable, the robot complies with the human's preference in order to retain their trust. In the shared autonomy setting, unlike many other common human-robot collaboration settings, only the robot actions can change the physical state of the world, and the human and robot goals are not fully observable. We address these challenges and show in a human subject experiment that the proposed mutual adaptation formalism improves human-robot team performance, while retaining a high level of user trust in the robot, compared to the common approach of having the robot strictly following participants' preference.

Factored Contextual Policy Search with Bayesian Optimization

Scarce data is a major challenge to scaling robot learning to truly complex tasks, as we need to generalize locally learned policies over different "contexts". Bayesian optimization approaches to contextual policy search (CPS) offer data-efficient policy learning that generalize over a context space. We propose to improve data- efficiency by factoring typically considered contexts into two components: target- type contexts that correspond to a desired outcome of the learned behavior, e.g. target position for throwing a ball; and environment type contexts that correspond to some state of the environment, e.g. initial ball position or wind speed. Our key observation is that experience can be directly generalized over target-type contexts. Based on that we introduce Factored Contextual Policy Search with Bayesian Optimization for both passive and active learning settings. Preliminary results show faster policy generalization on a simulated toy problem.

Configuration Lattices for Planar Contact Manipulation Under Uncertainty

This work addresses the challenge of a robot using real-time feedback from contact sensors to reliably manipulate a movable object on a cluttered tabletop. We formulate contact manipulation as a partially observable Markov decision process (POMDP) in the joint space of robot configurations and object poses. The POMDP formulation enables the robot to actively gather information and reduce the uncertainty on the object pose. Further, it incorporates all major constraints for robot manipulation: kinematic reachability, self-collision, and collision with obstacles. To solve the POMDP, we apply DESPOT, a state-of-the-art online POMDP algorithm. Our approach leverages two key ideas for computational efficiency. First, it performs lazy construction of a configuration-space lattice by interleaving construction of the lattice and online POMDP planning. Second, it combines online and offline POMDP planning by solving relaxed POMDP offline and using the solution to guide the online search algorithm. We evaluated the proposed approach on a seven degree-of-freedom robot arm in simulation environments. It significantly outperforms several existing algorithms, including some commonly used heuristics for contact manipulation under uncertainty.