ELEMENTAL: Interactive Learning from Demonstrations and Vision-Language Models for Reward Design in Robotics

Reinforcement learning (RL) has demonstrated compelling performance in robotic tasks, but its success often hinges on the design of complex, ad hoc reward functions. Researchers have explored how Large Language Models (LLMs) could enable non-expert users to specify reward functions more easily. However, LLMs struggle to balance the importance of different features, generalize poorly to out-of-distribution robotic tasks, and cannot represent the problem properly with only text-based descriptions. To address these challenges, we propose ELEMENTAL (intEractive LEarning froM dEmoNstraTion And Language), a novel framework that combines natural language guidance with visual user demonstrations to align robot behavior with user intentions better. By incorporating visual inputs, ELEMENTAL overcomes the limitations of text-only task specifications, while leveraging inverse reinforcement learning (IRL) to balance feature weights and match the demonstrated behaviors optimally. ELEMENTAL also introduces an iterative feedback-loop through self-reflection to improve feature, reward, and policy learning. Our experiment results demonstrate that ELEMENTAL outperforms prior work by 42.3% on task success, and achieves 41.3% better generalization in out-of-distribution tasks, highlighting its robustness in LfD.

Generating CAD Code with Vision-Language Models for 3D Designs

Generative AI has transformed the fields of Design and Manufacturing by providing efficient and automated methods for generating and modifying 3D objects. One approach involves using Large Language Models (LLMs) to generate Computer- Aided Design (CAD) scripting code, which can then be executed to render a 3D object; however, the resulting 3D object may not meet the specified requirements. Testing the correctness of CAD generated code is challenging due to the complexity and structure of 3D objects (e.g., shapes, surfaces, and dimensions) that are not feasible in code. In this paper, we introduce CADCodeVerify, a novel approach to iteratively verify and improve 3D objects generated from CAD code. Our approach works by producing ameliorative feedback by prompting a Vision-Language Model (VLM) to generate and answer a set of validation questions to verify the generated object and prompt the VLM to correct deviations. To evaluate CADCodeVerify, we introduce, CADPrompt, the first benchmark for CAD code generation, consisting of 200 natural language prompts paired with expert-annotated scripting code for 3D objects to benchmark progress. Our findings show that CADCodeVerify improves VLM performance by providing visual feedback, enhancing the structure of the 3D objects, and increasing the success rate of the compiled program. When applied to GPT-4, CADCodeVerify achieved a 7.30% reduction in Point Cloud distance and a 5.0% improvement in success rate compared to prior work

Learning Wheelchair Tennis Navigation from Broadcast Videos with Domain Knowledge Transfer and Diffusion Motion Planning

In this paper, we propose a novel and generalizable zero-shot knowledge transfer framework that distills expert sports navigation strategies from web videos into robotic systems with adversarial constraints and out-of-distribution image trajectories. Our pipeline enables diffusion-based imitation learning by reconstructing the full 3D task space from multiple partial views, warping it into 2D image space, closing the planning loop within this 2D space, and transfer constrained motion of interest back to task space. Additionally, we demonstrate that the learned policy can serve as a local planner in conjunction with position control. We apply this framework in the wheelchair tennis navigation problem to guide the wheelchair into the ball-hitting region. Our pipeline achieves a navigation success rate of 97.67% in reaching real-world recorded tennis ball trajectories with a physical robot wheelchair, and achieve a success rate of 68.49% in a real-world, real-time experiment on a full-sized tennis court.

Learning Dynamics of a Ball with Differentiable Factor Graph and Roto-Translational Invariant Representations

Robots in dynamic environments need fast, accurate models of how objects move in their environments to support agile planning. In sports such as ping pong, analytical models often struggle to accurately predict ball trajectories with spins due to complex aerodynamics, elastic behaviors, and the challenges of modeling sliding and rolling friction. On the other hand, despite the promise of data-driven methods, machine learning struggles to make accurate, consistent predictions without precise input. In this paper, we propose an end-to-end learning framework that can jointly train a dynamics model and a factor graph estimator. Our approach leverages a Gram-Schmidt (GS) process to extract roto-translational invariant representations to improve the model performance, which can further reduce the validation error compared to data augmentation method. Additionally, we propose a network architecture that enhances nonlinearity by using self-multiplicative bypasses in the layer connections. By leveraging these novel methods, our proposed approach predicts the ball's position with an RMSE of 37.2 mm of the paddle radius at the apex after the first bounce, and 71.5 mm after the second bounce.

Faster Model Predictive Control via Self-Supervised Initialization Learning

Optimization for robot control tasks, spanning various methodologies, includes Model Predictive Control (MPC). However, the complexity of the system, such as non-convex and non-differentiable cost functions and prolonged planning horizons often drastically increases the computation time, limiting MPC's real-world applicability. Prior works in speeding up the optimization have limitations on solving convex problem and generalizing to hold out domains. To overcome this challenge, we develop a novel framework aiming at expediting optimization processes. In our framework, we combine offline self-supervised learning and online fine-tuning through reinforcement learning to improve the control performance and reduce optimization time. We demonstrate the effectiveness of our method on a novel, challenging Formula-1-track driving task, achieving 3.9\% higher performance in optimization time and 3.6\% higher performance in tracking accuracy on challenging holdout tracks.

Designs for Enabling Collaboration in Human-Machine Teaming via Interactive and Explainable Systems

Collaborative robots and machine learning-based virtual agents are increasingly entering the human workspace with the aim of increasing productivity and enhancing safety. Despite this, we show in a ubiquitous experimental domain, Overcooked-AI, that state-of-the-art techniques for human-machine teaming (HMT), which rely on imitation or reinforcement learning, are brittle and result in a machine agent that aims to decouple the machine and human's actions to act independently rather than in a synergistic fashion. To remedy this deficiency, we develop HMT approaches that enable iterative, mixed-initiative team development allowing end-users to interactively reprogram interpretable AI teammates. Our 50-subject study provides several findings that we summarize into guidelines. While all approaches underperform a simple collaborative heuristic (a critical, negative result for learning-based methods), we find that white-box approaches supported by interactive modification can lead to significant team development, outperforming white-box approaches alone, and black-box approaches are easier to train and result in better HMT performance highlighting a tradeoff between explainability and interactivity versus ease-of-training. Together, these findings present three important directions: 1) Improving the ability to generate collaborative agents with white-box models, 2) Better learning methods to facilitate collaboration rather than individualized coordination, and 3) Mixed-initiative interfaces that enable users, who may vary in ability, to improve collaboration.

Mixed-Initiative Human-Robot Teaming under Suboptimality with Online Bayesian Adaptation

For effective human-agent teaming, robots and other artificial intelligence (AI) agents must infer their human partner's abilities and behavioral response patterns and adapt accordingly. Most prior works make the unrealistic assumption that one or more teammates can act near-optimally. In real-world collaboration, humans and autonomous agents can be suboptimal, especially when each only has partial domain knowledge. In this work, we develop computational modeling and optimization techniques for enhancing the performance of suboptimal human-agent teams, where the human and the agent have asymmetric capabilities and act suboptimally due to incomplete environmental knowledge. We adopt an online Bayesian approach that enables a robot to infer people's willingness to comply with its assistance in a sequential decision-making game. Our user studies show that user preferences and team performance indeed vary with robot intervention styles, and our approach for mixed-initiative collaborations enhances objective team performance ($p<.001$) and subjective measures, such as user's trust ($p<.001$) and perceived likeability of the robot ($p<.001$).

Efficient Trajectory Forecasting and Generation with Conditional Flow Matching

Trajectory prediction and generation are vital for autonomous robots navigating dynamic environments. While prior research has typically focused on either prediction or generation, our approach unifies these tasks to provide a versatile framework and achieve state-of-the-art performance. Diffusion models, which are currently state-of-the-art for learned trajectory generation in long-horizon planning and offline reinforcement learning tasks, rely on a computationally intensive iterative sampling process. This slow process impedes the dynamic capabilities of robotic systems. In contrast, we introduce Trajectory Conditional Flow Matching (T-CFM), a novel data-driven approach that utilizes flow matching techniques to learn a solver time-varying vector field for efficient and fast trajectory generation. We demonstrate the effectiveness of T-CFM on three separate tasks: adversarial tracking, real-world aircraft trajectory forecasting, and long-horizon planning. Our model outperforms state-of-the-art baselines with an increase of 35% in predictive accuracy and 142% increase in planning performance. Notably, T-CFM achieves up to 100$\times$ speed-up compared to diffusion-based models without sacrificing accuracy, which is crucial for real-time decision making in robotics.

Multi-Camera Asynchronous Ball Localization and Trajectory Prediction with Factor Graphs and Human Poses

The rapid and precise localization and prediction of a ball are critical for developing agile robots in ball sports, particularly in sports like tennis characterized by high-speed ball movements and powerful spins. The Magnus effect induced by spin adds complexity to trajectory prediction during flight and bounce dynamics upon contact with the ground. In this study, we introduce an innovative approach that combines a multi-camera system with factor graphs for real-time and asynchronous 3D tennis ball localization. Additionally, we estimate hidden states like velocity and spin for trajectory prediction. Furthermore, to enhance spin inference early in the ball's flight, where limited observations are available, we integrate human pose data using a temporal convolutional network (TCN) to compute spin priors within the factor graph. This refinement provides more accurate spin priors at the beginning of the factor graph, leading to improved early-stage hidden state inference for prediction. Our result shows the trained TCN can predict the spin priors with RMSE of 5.27 Hz. Integrating TCN into the factor graph reduces the prediction error of landing positions by over 63.6% compared to a baseline method that utilized an adaptive extended Kalman filter.

Interpretable Reinforcement Learning for Robotics and Continuous Control

Interpretability in machine learning is critical for the safe deployment of learned policies across legally-regulated and safety-critical domains. While gradient-based approaches in reinforcement learning have achieved tremendous success in learning policies for continuous control problems such as robotics and autonomous driving, the lack of interpretability is a fundamental barrier to adoption. We propose Interpretable Continuous Control Trees (ICCTs), a tree-based model that can be optimized via modern, gradient-based, reinforcement learning approaches to produce high-performing, interpretable policies. The key to our approach is a procedure for allowing direct optimization in a sparse decision-tree-like representation. We validate ICCTs against baselines across six domains, showing that ICCTs are capable of learning policies that parity or outperform baselines by up to 33% in autonomous driving scenarios while achieving a 300x-600x reduction in the number of parameters against deep learning baselines. We prove that ICCTs can serve as universal function approximators and display analytically that ICCTs can be verified in linear time. Furthermore, we deploy ICCTs in two realistic driving domains, based on interstate Highway-94 and 280 in the US. Finally, we verify ICCT's utility with end-users and find that ICCTs are rated easier to simulate, quicker to validate, and more interpretable than neural networks.