From therapeutic pocket robots and robot-assisted feeding systems, to “apprentice” robots and collaborative multi-robot teams, USC researchers are presenting these research topics and more at this year’s International Conference on Intelligent Robots and Systems (IROS). One of the world’s largest and most influential robotics conferences, taking place Oct 14-18 in Abu Dhabi, this year’s conference theme is “Robotics for Sustainable Development.”
Accepted USC papers areas of research including improving robotic learning processes, reactive planning for robot-human interactions, efficient robotic bin-packing and package transport, and enabling human influence on robot coordination.
Accepted papers with USC affiliation (USC authors highlighted):
Monday, October 14
ROMADO: 4th Workshop on Robotic Manipulation of Deformable Objects: Beyond Traditional Approaches
Daniel Seita
Tuesday, October 15
BayRnTune: Adaptive Bayesian Domain Randomization via Strategic Fine-tuning
Tianle Huang, Nitish Rajnish Sontakke, Kannabiran Niranjan Kumar, Irfan Essa, Stefanos Nikolaidis, Dennis W. Hong, Sehoon Ha
Abstract: Domain randomization (DR), which entails training a policy with randomized dynamics, has proven to be a simple yet effective algorithm for reducing the gap between simulation and the real world. However, DR often requires careful tuning of randomization parameters. Methods like Bayesian Domain Randomization (Bayesian DR) and Active Domain Randomization (Adaptive DR) address this issue by automating parameter range selection using real-world experience. While effective, these algorithms often require long computation time, as a new policy is trained from scratch every iteration. In this work, we propose Adaptive Bayesian Domain Randomization via Strategic Fine-tuning (BayRnTune), which inherits the spirit of BayRn but aims to significantly accelerate the learning processes by fine-tuning from previously learned policy. This idea leads to a critical question: which previous policy should we use as a prior during fine-tuning? We investigated four different fine-tuning strategies and compared them against baseline algorithms in five simulated environments, ranging from simple benchmark tasks to more complex legged robot environments. Our analysis demonstrates that our method yields better rewards in the same amount of timesteps compared to vanilla domain randomization or Bayesian DR.
Wednesday, October 16
ViSaRL: Visual Reinforcement Learning Guided by Human Saliency
Anthony Liang, Jesse Thomason, Erdem Bıyık
Abstract: Training robots to perform complex control tasks from high-dimensional pixel input using reinforcement learning (RL) is sample-inefficient, because image observations are comprised primarily of task-irrelevant information. By contrast, humans are able to visually attend to task-relevant objects and areas. Based on this insight, we introduce Visual Saliency-Guided Reinforcement Learning (ViSaRL). Using ViSaRL to learn visual representations significantly improves the success rate, sample efficiency, and generalization of an RL agent on diverse tasks including DeepMind Control benchmark, robot manipulation in simulation and on a real robot. We present approaches for incorporating saliency into both CNN and Transformer-based encoders. We show that visual representations learned using ViSaRL are robust to various sources of visual perturbations including perceptual noise and scene variations. ViSaRL nearly doubles success rate on the real-robot tasks compared to the baseline which does not use saliency.
Omey Mohan Manyar, Hantao Ye, Meghana Sagare, Siddharth Mayya, Fan Wang, Satyandra K. Gupta
Abstract: Bin-packing is an important problem in the robotic warehouse domain. Traditionally, this problem has been studied only for rigid packages (e.g., boxes or rigid objects). In this work, we tackle the problem of bin-packing with deformable packages that have become a popular choice for fulfillment needs. We present a system that incorporates a dual robot arm bimanual setup, uniquely combining suction and sweeping motions to stably and reliably pack deformable packages in a bin. Additionally, we propose a comprehensive action prediction framework to optimize for bin-packing efficiency by predicting optimal actions for both robots involved. Our methodology leverages a two-pronged learning strategy, where initially, we train a model in a self-supervised manner to predict a scoring metric indicative of bin-packing efficiency and then leverage an online optimization scheme to compute optimal actions in real time. The model is pre-trained in simulation in MuJoCo and fine-tuned on small-scale data from a real-world laboratory setting. Our packing score prediction model predicts bin-packing score in [0,1] with an MSE of 0.003. Real-world experiments validate our method’s adaptability to novel scenarios and its effectiveness in packing operations. Project Website: https://sites.google.com/usc.edu/bimanual-binpacking/.
Thursday, October 17
Blending Distributed NeRFs with Tri-Stage Robust Pose Optimization
Baijun Ye, Caiyun Liu, Xiaoyu Ye, Yuantao Chen, Yuhai Wang, Zike Yan, Yongliang Shi, Hao Zhao, Guyue Zhou
Abstract: Due to the limited model capacity, leveraging distributed Neural Radiance Fields (NeRFs) for modeling extensive urban environments has become a necessity. However, current distributed NeRF registration approaches encounter aliasing artifacts, arising from discrepancies in rendering resolutions and suboptimal pose precision. These factors collectively deteriorate the fidelity of pose estimation within NeRF frameworks, resulting in occlusion artifacts during the NeRF blending stage. In this paper, we present a distributed NeRF system with tri-stage pose optimization. In the first stage, precise poses of images are achieved by bundle adjusting Mip-NeRF 360 with a coarse-to-fine strategy. In the second stage, we incorporate the inverting Mip-NeRF 360, coupled with the truncated dynamic low-pass filter, to enable the achievement of robust and precise poses, termed Frame2Model optimization. On top of this, we obtain a coarse transformation between NeRFs in different coordinate systems. In the third stage, we fine-tune the transformation between NeRFs by Model2Model pose optimization. After obtaining precise transformation parameters, we proceed to implement NeRF blending, showcasing superior performance metrics in both real-world and simulation scenarios. Codes and data will be publicly available at https://github.com/boilcy/Distributed-NeRF.
Guangyao Shi, Gaurav S. Sukhatme
Abstract: We consider a new type of inverse combinatorial optimization, Inverse Submodular Maximization (ISM), for human-in-the-loop multi-robot coordination. Forward combinatorial optimization, defined as the process of solving a combinatorial problem given the reward (cost)-related parameters, is widely used in multi-robot coordination. In the standard pipeline, the reward (cost)-related parameters are designed offline by domain experts first and then these parameters are utilized for coordinating robots online. What if we need to change these parameters by non-expert human supervisors who watch over the robots during tasks to adapt to some new requirements? We are interested in the case where human supervisors can suggest what actions to take and the robots need to change the internal parameters based on such suggestions. We study such problems from the perspective of inverse combinatorial optimization, i.e., the process of finding parameters given solutions to the problem. Specifically, we propose a new formulation for ISM, in which we aim to find a new set of parameters that minimally deviate from the current parameters and can make the greedy algorithm output actions the same as those suggested by humans. We show that such problems can be formulated as a Mixed Integer Quadratic Program (MIQP). However, MIQP involves exponentially binary variables, making it intractable for the existing solver when the problem size is large. We propose a new algorithm under the Branch & Bound paradigm to solve such problems. In numerical simulations, we demonstrate how to use ISM in multi-robot multi-objective coverage control, and we show that the proposed algorithm achieves significant advantages in running time and peak memory usage compared to directly using the existing solver.
LAVA: Long-horizon Visual Action based Food Acquisition
Amisha Bhaskar, Rui Liu, Vishnu D. Sharma, Guangyao Shi, Pratap Tokekar
Abstract: Robotic Assisted Feeding (RAF) addresses the fundamental need for individuals with mobility impairments to regain autonomy in feeding themselves. The goal of RAF is to use a robot arm to acquire and transfer food to individuals from the table. Existing RAF methods primarily focus on solid foods, leaving a gap in manipulation strategies for semi- solid and deformable foods. We present Long-horizon Visual Action-based (LAVA) food acquisition of liquid, semisolid, and deformable foods. Long-horizon refers to the goal of “clearing the bowl” by sequentially acquiring the food from the bowl. LAVA is hierarchical: (1) At the highest level, we determine primitives using ScoopNet. (2) At the mid-level, LAVA finds parameters for the low-level primitives. (3) At the lowest level, LAVA carries out action execution using behaviour cloning. We validate LAVA on real-world acquisition trials involving granular, liquid, semisolid, and deformable foods along with fruit chunks and soup. Across 46 bowls, LAVA acquires much more efficiently than baselines with a success rate of 89 ± 4%, and generalizes across realistic plate variations such as varying positions, varieties, and amount of food in the bowl. Datasets and supplementary materials can be found on our website.
Cho-Ying Wu, Yiqi Zhong, Junying Wang, Ulrich Neumann
Abstract: Indoor robots rely on depth to perform tasks like navigation or obstacle detection, and single-image depth estimation is widely used to assist perception. Most indoor single-image depth prediction focuses less on model generalizability to unseen datasets, concerned with in-the-wild robustness for system deployment. This work leverages gradient-based meta-learning to gain higher generalizability on zero-shot cross-dataset inference. Unlike the most-studied meta-learning of image classification associated with explicit class labels, no explicit task boundaries exist for continuous depth values tied to highly varying indoor environments regarding object arrangement and scene composition. We propose fine-grained task that treats each RGB-D mini-batch as a task in our meta-learning formulation. We first show that our method on limited data induces a much better prior (max 27.8% in RMSE). Then, finetuning on meta-learned initialization consistently outperforms baselines without the meta approach. Aiming at generalization, we propose zero-shot cross-dataset protocols and validate higher generalizability induced by our meta-initialization, as a simple and useful plugin to many existing depth estimation methods. The work at the intersection of depth and meta-learning potentially drives both research to step closer to practical robotic and machine perception usage.
Signal Temporal Logic-Guided Apprenticeship Learning
Aniruddh Gopinath Puranic, Jyotirmoy Deshmukh, Stefanos Nikolaidis
Abstract: Apprenticeship learning crucially depends on effectively learning rewards, and hence control policies from user demonstrations. Of particular difficulty is the setting where the desired task consists of a number of sub-goals with temporal dependencies. The quality of inferred rewards and hence policies are typically limited by the quality of demonstrations, and poor inference of these can lead to undesirable outcomes. In this paper, we show how temporal logic specifications that describe high level task objectives, are encoded in a graph to define a temporal-based metric that reasons about behaviors of demonstrators and the learner agent to improve the quality of inferred rewards and policies. Through experiments on a diverse set of robot manipulator simulations, we show how our framework overcomes the drawbacks of prior literature by drastically improving the number of demonstrations required to learn a control policy.
Performing Efficient and Safe Deformable Package Transport Operations Using Suction Cups
Friday, October 18
Rishabh Shukla, Zeren Yu, Samrudh Moode, Omey Mohan Manyar, Fan Wang, Siddharth Mayya, Satyandra K. Gupta
Abstract: Suction cups are popular for picking and transporting packages in warehouse applications. To maximize throughput, high transport speeds are desired. Many packages are deformable and may detach from the suction cups due to inertial loading if trajectories use excessive velocities. This paper introduces a novel methodology that analyzes package deformation through its curvature at the package-suction cup contact interface to generate a Factor-of-Safety (FOS) score for each waypoint in a given trajectory. By maintaining the FOS above a predetermined threshold, the trajectory planner is able to generate transport trajectories that are both safe and time-optimized. Experimental results show the method’s efficacy, demonstrating a 21.92% reduction in transport times compared to a conservative trajectory generation.
Reactive Temporal Logic-based Planning and Control for Interactive Robotic Tasks
Farhad Nawaz Savvas Sadiq Ali, Shaoting Peng, Lars Lindemann, Nadia Figueroa, Nikolai Matni
Abstract: Robots interacting with humans must be safe, reactive and adapt online to unforeseen environmental and task changes. Achieving these requirements concurrently is a challenge as interactive planners lack formal safety guarantees, while safe motion planners lack flexibility to adapt. To tackle this, we propose a modular control architecture that generates both safe and reactive motion plans for human-robot interaction by integrating temporal logic-based discrete task level plans with continuous Dynamical System (DS)-based motion plans. We formulate a reactive temporal logic formula that enables users to define task specifications through structured language, and propose a planning algorithm at the task level that generates a sequence of desired robot behaviors while being adaptive to environmental changes. At the motion level, we incorporate control Lyapunov functions and control barrier functions to compute stable and safe continuous motion plans for two types of robot behaviors: (i) complex, possibly periodic motions given by autonomous DS and (ii) time-critical tasks specified by Signal Temporal Logic~(STL). Our methodology is demonstrated on the Franka robot arm performing wiping tasks on a whiteboard and a mannequin that is compliant to human interactions and adaptive to environmental changes.
Motion Planning for Automata-based Objectives using Efficient Gradient-based Methods
Anand Balakrishnan, Merve Atasever, Jyotirmoy Deshmukh
Abstract: In recent years, there has been increasing interest in using formal methods-based techniques to safely achieve temporal tasks, such as timed sequence of goals, or patrolling objectives. Such tasks are often expressed in real-time logics such as Signal Temporal Logic (STL), whereby, the logical specification is encoded into an optimization problem. Such approaches usually involve optimizing over the quantitative semantics, or robustness degree, of the logic over bounded horizons: the semantics can be encoded as mixed-integer linear constraints or into smooth approximations of the robustness degree. A major limitation of this approach is that it faces scalability challenges with respect to temporal complexity: for example, encoding long-term tasks requires storing the entire history of the system. In this paper, we present a quantitative generalization of such tasks in the form of symbolic automata objectives. Specifically, we show that symbolic automata can be expressed as matrix operators that lend themselves to automatic differentiation, allowing for the use of off-the-shelf gradient-based optimizers. We show how this helps solve the need to store arbitrarily long system trajectories, while efficiently leveraging the task structure encoded in the automaton.
Tactile Comfort: Lowering Heart Rate Through Touch Interactions with a Therapeutic Pocket Robot
Morten Roed Frederiksen, Kasper Stoy, Maja Matarić
Abstract: Children diagnosed with anxiety disorders are taught a range of strategies to navigate situations of heightened anxiety. Techniques such as deep breathing and repetition of mantras are commonly employed, as they are known to be calming and reduce elevated heart rates. Although these strategies are often effective, their successful application relies on prior training of the children for successful use when faced with challenging situations. This paper investigates a pocket- sized companion robot designed to offer a relaxation technique requiring no prior training, with a focus on immediate impact on the user’s heart rate. The robot utilizes a tactile game to divert the user’s attention, thereby promoting relaxation. We conducted two studies with children who were not diagnosed with anxiety: a 14-day pilot study with two children (age 8) and a main study with 18 children (ages 5-7). Both studies employed a within-subjects design and focused on measuring heart rate during tactile interaction with the robot and during non-use. Interacting with the robot was found to significantly lower the study participants’ heart rate (p<0.01) compared to the non- use condition, indicating a consistent calming effect across all participants. These results suggest that tactile companion robots have the potential to enhance the therapeutic value of relaxation techniques.
Published on October 15th, 2024
Last updated on October 16th, 2024
