Learning to manipulate objects efficiently, particularly those involving sustained contact (e.g., pushing, sliding) and articulated parts (e.g., drawers, doors), presents significant challenges. Traditional methods, such as robot-centric reinforce-ment learning (RL), imitation learning, and hybrid techniques, require massive training and often struggle to generalize across different objects and robot platforms. We propose a novel framework for learning object-centric manipulation policies in force space, decoupling the robot from the object. By directly applying forces to selected regions of the object, our method simplifies the action space, reduces unnecessary exploration, and decreases simulation overhead. This approach, trained in simulation on a small set of representative objects, captures ob-ject dynamics—such as joint configurations—allowing policies to generalize effectively to new, unseen objects. Decoupling these policies from robot-specific dynamics enables direct transfer to different robotic platforms (e.g., Kinova, Panda, URS) with-out retraining. Our evaluations demonstrate that the method significantly outperforms baselines, achieving over an order of magnitude improvement in training efficiency compared to other state-of-the-art methods. Additionally, operating in force space enhances policy transferability across diverse robot plat-forms and object types. We further showcase the applicability of our method in a real-world robotic setting. Link: https://tufts-ai-robotics-group.github.io/FLEX/

In dynamic open-world environments, agents continually face new challenges due to sudden and unpredictable novelties, hindering Task and Motion Planning (TAMP) in autonomous systems. We introduce a novel TAMP architecture that integrates symbolic planning with reinforcement learning to enable autonomous adaptation in such environments, operating without human guidance. Our approach employs symbolic goal representation within a goal-oriented learning framework, coupled with planner-guided goal identification, effectively managing abrupt changes where traditional reinforcement learning, re-planning, and hybrid methods fall short. Through sequential novelty injections in our experiments, we assess our method’s adaptability to continual learning scenarios. Extensive simulations conducted in a robotics domain corroborate the superiority of our approach, demonstrating faster convergence to higher performance compared to traditional methods. The success of our framework in navigating diverse novelty scenarios within a continuous domain underscores its potential for critical real-world applications.

Despite recent progress in Reinforcement Learning for robotics applications, many tasks remain prohibitively difficult to solve because of the expensive interaction cost. Transfer learning helps reduce the training time in the target domain by transferring knowledge learned in a source domain. Sim2Real transfer helps transfer knowledge from a simulated robotic domain to a physical target domain. Knowledge transfer reduces the time required to train a task in the physical world, where the cost of interactions is high. However, most existing approaches assume exact correspondence in the task structure and the physical properties of the two domains. This work proposes a framework for Few-Shot Policy Transfer between two domains through Observation Mapping and Behavior Cloning. We use Generative Adversarial Networks (GANs) along with a cycle-consistency loss to map the observations between the source and target domains and later use this learned mapping to clone the successful source task behavior policy to the target domain. We observe successful behavior policy transfer with limited target task interactions and in cases where the source and target task are semantically dissimilar.

Robotics in healthcare has recently emerged, backed by the recent advances in the field of machine learning and robotics. Researchers are focusing on training robots for interacting with elderly adults. This research primarily focuses on engineering more efficient robots that can learn from their mistakes, thereby aiding in better human-robot interaction. In this work, we propose a method in which a robot learns to navigate itself to the individual in need. The robotic agents' learning algorithm will be capable of navigating in an unknown environment. The robot's primary objective is to locate human in a house, and upon finding the human, the goal is to interact with them while complementing their pose and gaze. We propose an end to end learning strategy, which uses a recurrent neural network architecture in combination with Q-learning to train an optimal policy. The idea can be a contribution to better human-robot interaction.