Mohan Sridharan

Nandiraju Gireesh, D. A. Sasi Kiran, Snehasis Banerjee et al.

Object Goal Navigation requires a robot to find and navigate to an instance of a target object class in a previously unseen environment. Our framework incrementally builds a semantic map of the environment over time, and then repeatedly selects a long-term goal ('where to go') based on the semantic map to locate the target object instance. Long-term goal selection is formulated as a vision-based deep reinforcement learning problem. Specifically, an Encoder Network is trained to extract high-level features from a semantic map and select a long-term goal. In addition, we incorporate data augmentation and Q-function regularization to make the long-term goal selection more effective. We report experimental results using the photo-realistic Gibson benchmark dataset in the AI Habitat 3D simulation environment to demonstrate substantial performance improvement on standard measures in comparison with a state of the art data-driven baseline.

Hasra Dodampegama, Mohan Sridharan

Ad hoc teamwork refers to the problem of enabling an agent to collaborate with teammates without prior coordination. Data-driven methods represent the state of the art in ad hoc teamwork. They use a large labeled dataset of prior observations to model the behavior of other agent types and to determine the ad hoc agent's behavior. These methods are computationally expensive, lack transparency, and make it difficult to adapt to previously unseen changes, e.g., in team composition. Our recent work introduced an architecture that determined an ad hoc agent's behavior based on non-monotonic logical reasoning with prior commonsense domain knowledge and predictive models of other agents' behavior that were learned from limited examples. In this paper, we substantially expand the architecture's capabilities to support: (a) online selection, adaptation, and learning of the models that predict the other agents' behavior; and (b) collaboration with teammates in the presence of partial observability and limited communication. We illustrate and experimentally evaluate the capabilities of our architecture in two simulated multiagent benchmark domains for ad hoc teamwork: Fort Attack and Half Field Offense. We show that the performance of our architecture is comparable or better than state of the art data-driven baselines in both simple and complex scenarios, particularly in the presence of limited training data, partial observability, and changes in team composition.

D. A. Sasi Kiran, Kritika Anand, Chaitanya Kharyal et al.

This paper describes a framework for the object-goal navigation task, which requires a robot to find and move to the closest instance of a target object class from a random starting position. The framework uses a history of robot trajectories to learn a Spatial Relational Graph (SRG) and Graph Convolutional Network (GCN)-based embeddings for the likelihood of proximity of different semantically-labeled regions and the occurrence of different object classes in these regions. To locate a target object instance during evaluation, the robot uses Bayesian inference and the SRG to estimate the visible regions, and uses the learned GCN embeddings to rank visible regions and select the region to explore next.

Hasra Dodampegama, Mohan Sridharan

We present an architecture for ad hoc teamwork, which refers to collaboration in a team of agents without prior coordination. State of the art methods for this problem often include a data-driven component that uses a long history of prior observations to model the behaviour of other agents (or agent types) and to determine the ad hoc agent's behaviour. In many practical domains, it is challenging to find large training datasets, and necessary to understand and incrementally extend the existing models to account for changes in team composition or domain attributes. Our architecture combines the principles of knowledge-based and data-driven reasoning and learning. Specifically, we enable an ad hoc agent to perform non-monotonic logical reasoning with prior commonsense domain knowledge and incrementally-updated simple predictive models of other agents' behaviour. We use the benchmark simulated multi-agent collaboration domain Fort Attack to demonstrate that our architecture supports adaptation to unforeseen changes, incremental learning and revision of models of other agents' behaviour from limited samples, transparency in the ad hoc agent's decision making, and better performance than a data-driven baseline.

Raul D. Steleac, Mohan Sridharan, David Abel

Temporally extended actions improve the ability to explore and plan in single-agent settings. In multi-agent settings, the exponential growth of the joint state space with the number of agents makes coordinated behaviours even more valuable. Yet, this same exponential growth renders the design of multi-agent options particularly challenging. Existing multi-agent option discovery methods often sacrifice coordination by producing loosely coupled or fully independent behaviours. Toward addressing these limitations, we describe a novel approach for multi-agent option discovery. Specifically, we propose a joint-state abstraction that compresses the state space while preserving the information necessary to discover strongly coordinated behaviours. Our approach builds on the inductive bias that synchronisation over agent states provides a natural foundation for coordination in the absence of explicit objectives. We first approximate a fictitious state of maximal alignment with the team, the \textit{Fermat} state, and use it to define a measure of \textit{spreadness}, capturing team-level misalignment on each individual state dimension. Building on this representation, we then employ a neural graph Laplacian estimator to derive options that capture state synchronisation patterns between agents. We evaluate the resulting options across multiple scenarios in two multi-agent domains, showing that they yield stronger downstream coordination capabilities compared to alternative option discovery methods.

Raghav Arora, Shivam Singh, Karthik Swaminathan et al. · mit

Assistive agents performing household tasks such as making the bed or cooking breakfast often compute and execute actions that accomplish one task at a time. However, efficiency can be improved by anticipating upcoming tasks and computing an action sequence that jointly achieves these tasks. State-of-the-art methods for task anticipation use data-driven deep networks and Large Language Models (LLMs), but they do so at the level of high-level tasks and/or require many training examples. Our framework leverages the generic knowledge of LLMs through a small number of prompts to perform high-level task anticipation, using the anticipated tasks as goals in a classical planning system to compute a sequence of finer-granularity actions that jointly achieve these goals. We ground and evaluate our framework's abilities in realistic scenarios in the VirtualHome environment and demonstrate a 31% reduction in execution time compared with a system that does not consider upcoming tasks.

Shivam Singh, Karthik Swaminathan, Nabanita Dash et al.

An embodied agent assisting humans is often asked to complete new tasks, and there may not be sufficient time or labeled examples to train the agent to perform these new tasks. Large Language Models (LLMs) trained on considerable knowledge across many domains can be used to predict a sequence of abstract actions for completing such tasks, although the agent may not be able to execute this sequence due to task-, agent-, or domain-specific constraints. Our framework addresses these challenges by leveraging the generic predictions provided by LLM and the prior domain knowledge encoded in a Knowledge Graph (KG), enabling an agent to quickly adapt to new tasks. The robot also solicits and uses human input as needed to refine its existing knowledge. Based on experimental evaluation in the context of cooking and cleaning tasks in simulation domains, we demonstrate that the interplay between LLM, KG, and human input leads to substantial performance gains compared with just using the LLM. Project website§: https://sssshivvvv.github.io/adaptbot/

Oliver Kim, Mohan Sridharan

Landmarks are facts or actions that appear in all valid solutions of a planning problem. They have been used successfully to calculate heuristics that guide the search for a plan. We investigate an extension to this concept by defining a novel "relevance score" that helps identify facts or actions that appear in most but not all plans to achieve any given goal. We describe an approach to compute this relevance score and use it as a heuristic in the search for a plan. We experimentally compare the performance of our approach with that of a state of the art landmark-based heuristic planning approach using benchmark planning problems. While the original landmark-based heuristic leads to better performance on problems with well-defined landmarks, our approach substantially improves performance on problems that lack non-trivial landmarks.

Hasra Dodampegama, Mohan Sridharan

AI agents deployed in assistive roles often have to collaborate with other agents (humans, AI systems) without prior coordination. Methods considered state of the art for such ad hoc teamwork often pursue a data-driven approach that needs a large labeled dataset of prior observations, lacks transparency, and makes it difficult to rapidly revise existing knowledge in response to changes. As the number of agents increases, the complexity of decision-making makes it difficult to collaborate effectively. This paper advocates leveraging the complementary strengths of knowledge-based and data-driven methods for reasoning and learning for ad hoc teamwork. For any given goal, our architecture enables each ad hoc agent to determine its actions through non-monotonic logical reasoning with: (a) prior commonsense domain-specific knowledge; (b) models learned and revised rapidly to predict the behavior of other agents; and (c) anticipated abstract future goals based on generic knowledge of similar situations in an existing foundation model. We experimentally evaluate our architecture's capabilities in VirtualHome, a realistic physics-based 3D simulation environment.

Shivam Singh, Karthik Swaminathan, Raghav Arora et al.

An agent assisting humans in daily living activities can collaborate more effectively by anticipating upcoming tasks. Data-driven methods represent the state of the art in task anticipation, planning, and related problems, but these methods are resource-hungry and opaque. Our prior work introduced a proof of concept framework that used an LLM to anticipate 3 high-level tasks that served as goals for a classical planning system that computed a sequence of low-level actions for the agent to achieve these goals. This paper describes DaTAPlan, our framework that significantly extends our prior work toward human-robot collaboration. Specifically, DaTAPlan planner computes actions for an agent and a human to collaboratively and jointly achieve the tasks anticipated by the LLM, and the agent automatically adapts to unexpected changes in human action outcomes and preferences. We evaluate DaTAPlan capabilities in a realistic simulation environment, demonstrating accurate task anticipation, effective human-robot collaboration, and the ability to adapt to unexpected changes. Project website: https://dataplan-hrc.github.io

Nandiraju Gireesh, Ayush Agrawal, Ahana Datta et al.

The Multi-Object Navigation (MultiON) task requires a robot to localize an instance (each) of multiple object classes. It is a fundamental task for an assistive robot in a home or a factory. Existing methods for MultiON have viewed this as a direct extension of Object Navigation (ON), the task of localising an instance of one object class, and are pre-sequenced, i.e., the sequence in which the object classes are to be explored is provided in advance. This is a strong limitation in practical applications characterized by dynamic changes. This paper describes a deep reinforcement learning framework for sequence-agnostic MultiON based on an actor-critic architecture and a suitable reward specification. Our framework leverages past experiences and seeks to reward progress toward individual as well as multiple target object classes. We use photo-realistic scenes from the Gibson benchmark dataset in the AI Habitat 3D simulation environment to experimentally show that our method performs better than a pre-sequenced approach and a state of the art ON method extended to MultiON.

Reuth Mirsky, Ignacio Carlucho, Arrasy Rahman et al.

Ad hoc teamwork is the research problem of designing agents that can collaborate with new teammates without prior coordination. This survey makes a two-fold contribution: First, it provides a structured description of the different facets of the ad hoc teamwork problem. Second, it discusses the progress that has been made in the field so far, and identifies the immediate and long-term open problems that need to be addressed in ad hoc teamwork.

Mohan Sridharan, Tiago Mota

Algorithms based on deep network models are being used for many pattern recognition and decision-making tasks in robotics and AI. Training these models requires a large labeled dataset and considerable computational resources, which are not readily available in many domains. Also, it is difficult to explore the internal representations and reasoning mechanisms of these models. As a step towards addressing the underlying knowledge representation, reasoning, and learning challenges, the architecture described in this paper draws inspiration from research in cognitive systems. As a motivating example, we consider an assistive robot trying to reduce clutter in any given scene by reasoning about the occlusion of objects and stability of object configurations in an image of the scene. In this context, our architecture incrementally learns and revises a grounding of the spatial relations between objects and uses this grounding to extract spatial information from input images. Non-monotonic logical reasoning with this information and incomplete commonsense domain knowledge is used to make decisions about stability and occlusion. For images that cannot be processed by such reasoning, regions relevant to the tasks at hand are automatically identified and used to train deep network models to make the desired decisions. Image regions used to train the deep networks are also used to incrementally acquire previously unknown state constraints that are merged with the existing knowledge for subsequent reasoning. Experimental evaluation performed using simulated and real-world images indicates that in comparison with baselines based just on deep networks, our architecture improves reliability of decision making and reduces the effort involved in training data-driven deep network models.

Mark Burstein, Mohan Sridharan, David McDonald

ACS is an annual meeting for research on the initial goals of artificial intelligence and cognitive science, which aimed to explain the mind in computational terms and to reproduce the entire range of human cognitive abilities in computational artifacts. Many researchers remain committed to this original vision, and Advances in Cognitive Systems provides a place to present recent results and pose new challenges for the field. The meetings bring together researchers with interests in human-level intelligence, complex cognition, integrated intelligent systems, cognitive architectures, and related topics.

Saif Sidhik, Mohan Sridharan, Dirk Ruiken

We describe a framework for changing-contact robot manipulation tasks that require the robot to make and break contacts with objects and surfaces. The discontinuous interaction dynamics of such tasks make it difficult to construct and use a single dynamics model or control strategy, and the highly non-linear nature of the dynamics during contact changes can be damaging to the robot and the objects. We present an adaptive control framework that enables the robot to incrementally learn to predict contact changes in a changing contact task, learn the interaction dynamics of the piece-wise continuous system, and provide smooth and accurate trajectory tracking using a task-space variable impedance controller. We experimentally compare the performance of our framework against that of representative control methods to establish that the adaptive control and incremental learning components of our framework are needed to achieve smooth control in the presence of discontinuous dynamics in changing-contact robot manipulation tasks.

Saif Sidhik, Mohan Sridharan, Dirk Ruiken

Many robot manipulation tasks require the robot to make and break contact with objects and surfaces. The dynamics of such changing-contact robot manipulation tasks are discontinuous when contact is made or broken, and continuous elsewhere. These discontinuities make it difficult to construct and use a single dynamics model or control strategy for any such task. We present a framework for smooth dynamics and control of such changing-contact manipulation tasks. For any given target motion trajectory, the framework incrementally improves its prediction of when contacts will occur. This prediction and a model relating approach velocity to impact force modify the velocity profile of the motion sequence such that it is $C^\infty$ smooth, and help achieve a desired force on impact. We implement this framework by building on our hybrid force-motion variable impedance controller for continuous contact tasks. We experimentally evaluate our framework in the illustrative context of sliding tasks involving multiple contact changes with transitions between surfaces of different properties.

Angel Daruna, Mehul Gupta, Mohan Sridharan et al.

In recent years, there has been a resurgence in methods that use distributed (neural) representations to represent and reason about semantic knowledge for robotics applications. However, while robots often observe previously unknown concepts, these representations typically assume that all concepts are known a priori, and incorporating new information requires all concepts to be learned afresh. Our work relaxes this limiting assumption of existing representations and tackles the incremental knowledge graph embedding problem by leveraging the principles of a range of continual learning methods. Through an experimental evaluation with several knowledge graphs and embedding representations, we provide insights about trade-offs for practitioners to match a semantics-driven robotics applications to a suitable continual knowledge graph embedding method.

Tiago Mota, Mohan Sridharan

A robot's ability to provide descriptions of its decisions and beliefs promotes effective collaboration with humans. Providing such transparency is particularly challenging in integrated robot systems that include knowledge-based reasoning methods and data-driven learning algorithms. Towards addressing this challenge, our architecture couples the complementary strengths of non-monotonic logical reasoning, deep learning, and decision-tree induction. During reasoning and learning, the architecture enables a robot to provide on-demand relational descriptions of its decisions, beliefs, and the outcomes of hypothetical actions. These capabilities are grounded and evaluated in the context of scene understanding tasks and planning tasks performed using simulated images and images from a physical robot manipulating tabletop objects.

Shiqi Zhang, Mohan Sridharan

Reasoning with declarative knowledge (RDK) and sequential decision-making (SDM) are two key research areas in artificial intelligence. RDK methods reason with declarative domain knowledge, including commonsense knowledge, that is either provided a priori or acquired over time, while SDM methods (probabilistic planning and reinforcement learning) seek to compute action policies that maximize the expected cumulative utility over a time horizon; both classes of methods reason in the presence of uncertainty. Despite the rich literature in these two areas, researchers have not fully explored their complementary strengths. In this paper, we survey algorithms that leverage RDK methods while making sequential decisions under uncertainty. We discuss significant developments, open problems, and directions for future work.

Heather Riley, Mohan Sridharan

State of the art algorithms for many pattern recognition problems rely on deep network models. Training these models requires a large labeled dataset and considerable computational resources. Also, it is difficult to understand the working of these learned models, limiting their use in some critical applications. Towards addressing these limitations, our architecture draws inspiration from research in cognitive systems, and integrates the principles of commonsense logical reasoning, inductive learning, and deep learning. In the context of answering explanatory questions about scenes and the underlying classification problems, the architecture uses deep networks for extracting features from images and for generating answers to queries. Between these deep networks, it embeds components for non-monotonic logical reasoning with incomplete commonsense domain knowledge, and for decision tree induction. It also incrementally learns and reasons with previously unknown constraints governing the domain's states. We evaluated the architecture in the context of datasets of simulated and real-world images, and a simulated robot computing, executing, and providing explanatory descriptions of plans. Experimental results indicate that in comparison with an ``end to end'' architecture of deep networks, our architecture provides better accuracy on classification problems when the training dataset is small, comparable accuracy with larger datasets, and more accurate answers to explanatory questions. Furthermore, incremental acquisition of previously unknown constraints improves the ability to answer explanatory questions, and extending non-monotonic logical reasoning to support planning and diagnostics improves the reliability and efficiency of computing and executing plans on a simulated robot.

Rocio Gomez, Mohan Sridharan, Heather Riley

The architecture described in this paper encodes a theory of intentions based on the the key principles of non-procrastination, persistence, and automatically limiting reasoning to relevant knowledge and observations. The architecture reasons with transition diagrams of any given domain at two different resolutions, with the fine-resolution description defined as a refinement of, and hence tightly-coupled to, a coarse-resolution description. Non-monotonic logical reasoning with the coarse-resolution description computes an activity (i.e., plan) comprising abstract actions for any given goal. Each abstract action is implemented as a sequence of concrete actions by automatically zooming to and reasoning with the part of the fine-resolution transition diagram relevant to the current coarse-resolution transition and the goal. Each concrete action in this sequence is executed using probabilistic models of the uncertainty in sensing and actuation, and the corresponding fine-resolution outcomes are used to infer coarse-resolution observations that are added to the coarse-resolution history. The architecture's capabilities are evaluated in the context of a simulated robot assisting humans in an office domain, on a physical robot (Baxter) manipulating tabletop objects, and on a wheeled robot (Turtlebot) moving objects to particular places or people. The experimental results indicate improvements in reliability and computational efficiency compared with an architecture that does not include the theory of intentions, and an architecture that does not include zooming for fine-resolution reasoning.

Ermano Arruda, Claudio Zito, Mohan Sridharan et al.

We present a parametric formulation for learning generative models for grasp synthesis from a demonstration. We cast new light on this family of approaches, proposing a parametric formulation for grasp synthesis that is computationally faster compared to related work and indicates better grasp success rate performance in simulated experiments, showing a gain of at least 10% success rate (p < 0.05) in all the tested conditions. The proposed implementation is also able to incorporate arbitrary constraints for grasp ranking that may include task-specific constraints. Results are reported followed by a brief discussion on the merits of the proposed methods noted so far.

Mohan Sridharan, Michael Gelfond, Shiqi Zhang et al.

This paper describes an architecture for robots that combines the complementary strengths of probabilistic graphical models and declarative programming to represent and reason with logic-based and probabilistic descriptions of uncertainty and domain knowledge. An action language is extended to support non-boolean fluents and non-deterministic causal laws. This action language is used to describe tightly-coupled transition diagrams at two levels of granularity, with a fine-resolution transition diagram defined as a refinement of a coarse-resolution transition diagram of the domain. The coarse-resolution system description, and a history that includes (prioritized) defaults, are translated into an Answer Set Prolog (ASP) program. For any given goal, inference in the ASP program provides a plan of abstract actions. To implement each such abstract action, the robot automatically zooms to the part of the fine-resolution transition diagram relevant to this action. A probabilistic representation of the uncertainty in sensing and actuation is then included in this zoomed fine-resolution system description, and used to construct a partially observable Markov decision process (POMDP). The policy obtained by solving the POMDP is invoked repeatedly to implement the abstract action as a sequence of concrete actions, with the corresponding observations being recorded in the coarse-resolution history and used for subsequent reasoning. The architecture is evaluated in simulation and on a mobile robot moving objects in an indoor domain, to show that it supports reasoning with violation of defaults, noisy observations and unreliable actions, in complex domains.

Zenon Colaco, Mohan Sridharan

Robots assisting humans in complex domains have to represent knowledge and reason at both the sensorimotor level and the social level. The architecture described in this paper couples the non-monotonic logical reasoning capabilities of a declarative language with probabilistic belief revision, enabling robots to represent and reason with qualitative and quantitative descriptions of knowledge and degrees of belief. Specifically, incomplete domain knowledge, including information that holds in all but a few exceptional situations, is represented as a Answer Set Prolog (ASP) program. The answer set obtained by solving this program is used for inference, planning, and for jointly explaining (a) unexpected action outcomes due to exogenous actions and (b) partial scene descriptions extracted from sensor input. For any given task, each action in the plan contained in the answer set is executed probabilistically. The subset of the domain relevant to the action is identified automatically, and observations extracted from sensor inputs perform incremental Bayesian updates to a belief distribution defined over this domain subset, with highly probable beliefs being committed to the ASP program. The architecture's capabilities are illustrated in simulation and on a mobile robot in the context of a robot waiter operating in the dining room of a restaurant.

Shiqi Zhang, Mohan Sridharan, Michael Gelfond et al.

This paper describes an architecture that combines the complementary strengths of declarative programming and probabilistic graphical models to enable robots to represent, reason with, and learn from, qualitative and quantitative descriptions of uncertainty and knowledge. An action language is used for the low-level (LL) and high-level (HL) system descriptions in the architecture, and the definition of recorded histories in the HL is expanded to allow prioritized defaults. For any given goal, tentative plans created in the HL using default knowledge and commonsense reasoning are implemented in the LL using probabilistic algorithms, with the corresponding observations used to update the HL history. Tight coupling between the two levels enables automatic selection of relevant variables and generation of suitable action policies in the LL for each HL action, and supports reasoning with violation of defaults, noisy observations and unreliable actions in large and complex domains. The architecture is evaluated in simulation and on physical robots transporting objects in indoor domains; the benefit on robots is a reduction in task execution time of 39% compared with a purely probabilistic, but still hierarchical, approach.

Shiqi Zhang, Mohan Sridharan

For widespread deployment in domains characterized by partial observability, non-deterministic actions and unforeseen changes, robots need to adapt sensing, processing and interaction with humans to the tasks at hand. While robots typically cannot process all sensor inputs or operate without substantial domain knowledge, it is a challenge to provide accurate domain knowledge and humans may not have the time and expertise to provide elaborate and accurate feedback. The architecture described in this paper combines declarative programming and probabilistic reasoning to address these challenges, enabling robots to: (a) represent and reason with incomplete domain knowledge, resolving ambiguities and revising existing knowledge using sensor inputs and minimal human feedback; and (b) probabilistically model the uncertainty in sensor input processing and navigation. Specifically, Answer Set Programming (ASP), a declarative programming paradigm, is combined with hierarchical partially observable Markov decision processes (POMDPs), using domain knowledge to revise probabilistic beliefs, and using positive and negative observations for early termination of tasks that can no longer be pursued. All algorithms are evaluated in simulation and on mobile robots locating target objects in indoor domains.